How-To Tutorials - Artificial Intelligence

Generative adversarial networks (GANs) have been at the forefront of research on generative models in the last couple of years. GANs have been used for image generation, image processing, image synthesis from captions, image editing, visual domain adaptation, data generation for visual recognition, and many other applications, often leading to state of the art results. One of the tutorials titled, ‘Generative Adversarial Networks’ conducted at the CVPR 2018 (a Conference on Computer Vision and Pattern Recognition held at Salt Lake City, USA) provides a broad overview of generative adversarial networks and how GANs can be trained to perform different purposes.  The tutorial involved various speakers sharing basic concepts, best practices of the current state-of-the-art GAN including network architectures, objective functions, other training tricks, and much more. Let us look at how GANs are trained for different use cases.  There’s more to GANs….. If you further want to explore different examples of modern GAN implementations, including CycleGAN, simGAN, DCGAN, and 2D image to 3D model generation, you can explore the book, Generative Adversarial Networks Cookbook written by Josh Kalin. The recipes given in this cookbook will help you build on a common architecture in Python, TensorFlow and Keras to explore increasingly difficult GAN architectures in an easy-to-read format. Training GANs for object detection using Adversarial Learning Xialong Wang, from Carnegie Mellon University talked about object detection in computer vision as well as from the context of taking actions in robots. He also explained how to use adversarial learning for instances beyond image generation. To train a GAN, the key idea is to find the adversarial tasks for your target tasks to improve your target by fighting against these adversarial tasks. In computer vision if your target task is to recognize a bird using object detection, one adversarial task is adding occlusions by generating a mask to accrue the bird’s head and its leg which will make it difficult for the detector to recognize. The detector will further try to conquer these difficult tasks and from then on it will become robust to Occlusions. Another adversarial task for object detection can be Deformations. Here the image can be slightly rotated to make the detection difficult.  For training robots to grasp objects, one of the adversaries would be the Shaking test. If the robot arm is stable enough the object it grasps should not fall even with a rigourous shake. Another example is snatching. If another arm can snatch easily, it means it is not completely trained to resist snatching or stealing. Wang said the CMU research team tried generating images using DCGAN on the COCO dataset. However, the images generated could not assist in training the detector as the detectors could easily detect them as false images. Next, the team generated images using Conditional GANs on COCO but these didn’t help either. Hence, the team generated hard positive examples in feed by adding real world occlusions or real world deformations to challenge the detectors. He then talked about a Standard Fast R-CNN Detector which takes an image input in the convolutional neural network language model. After taking the input, the detector extracts features for the whole image, and later you can crop the features according to the proposal bounding box. These cropped features are resized to channel (C*6*6); here 6*6 is interred spatial dimensions. These features are the object features you want to focus on and can also use them to perform classification or regression for detections. The team has added a small network in the middle that would input the extracted features and generate a mask. The mask will assist which spatial locations to chop out certain features that would make it hard for the detectors to recognize. He also shared the benchmark results of the tests using different datasets like the AlexNet, VGG16, FRCN, and so on. The ASTN and the ASDN model showed improved output over the other networks.   Understanding Generative Adversarial Imitation Learning (GAIL) for training a machine to imitate human behaviours Stefano Ermon from Stanford University explained how to use Generative modeling ideas and GAN training to imitate human behaviours in complex environments.  A lot of progress in reinforcement learning has been made with successes in playing board games such as Chess, video games, and so on. However, Reinforcement Learning has one limitation. If you want to use it to solve a new task you have to specify a cost signal / a reward signal to provide some supervision to your reinforcement learning algorithm. You also need to specify what kind of behaviors are desirable and which are not.   In a game scenario the cost signal is whether you win or you lose. However, in further complex tasks like driving an autonomous vehicles to specify a cost signal becomes difficult as there are different objective functions like going off road, not moving above the speed limit, avoiding a road crash, and much more.  The simplest method one can use is Behavioural cloning where you can use your trajectories and your demonstrations to construct a training set of states with the corresponding action that the expert took in those states. You can further use your favorite supervised learning method classification or regression if the actions are continuous. However, this has some limitations: Small errors may compound over time as the learning algorithm will make certain mistakes initially and these mistakes will lead towards never seen before states or objects. It is like a Black box approach where every decision requires initial planning. Ermon suggests an alternative to imitation could be an Inverse RL (IRL) approachHe also demonstrates the similarities between RL and IRL. For the complete demonstration, you can check out the video.  The main difference between a GAIL and GANs is that in GANs the generator is taking inputs, random noise and maps them to the neural network producing some samples for the detector. However, in GAIL, the generator is more complex as it includes two components, a policy P which you can train and an environment (Black Box simulator) that can’t be controlled. What matters is the distribution over states and actions that you encounter when you navigate the environment using the policy that can be tuned. As the environment is difficult to control, training the GAIL model is harder than the simple GANs model. On the other hand, in a GANs model, training the policy is challenging such that the discriminator goes into the direction of fooling.  However, GAIL is the easier generative modelling task because you don’t have to learn the whole thing end to end and neither do you have to come up with a large neural network that maps noise into behaviours as some part of the input is given by the environment. But it is harder to train because you don't really know how the black box works. Ermon further explains how using Generative Adversarial Imitation Learning, one can not only imitate complex behaviors, but also learn interpretable and meaningful representations of complex behavioral data, including visual demonstrations with a method named as InfoGAN, a method, built on top of GAIL.   He also explained a new framework for multi-agent imitation learning for general Markov games by integrating multi-agent RL with a suitable extension of multi-agent inverse RL. This method will generalize Generative Adversarial Imitation Learning (GAIL) in the single agent case. This method will successfully imitate complex behaviors in high-dimensional environments with multiple cooperative or competing agents. To know more about further demonstrations on GAIL, InfoGAIL, and Multi-agent GAIL, watch the complete video on YouTube. Knowing the basics isn’t enough, putting them to practice is necessary. If you want to use GANs practically and experiment with them, Generative Adversarial Networks Cookbook by Josh Kalin is your go-to guide. With this cookbook, you will work with use cases involving DCGAN, Pix2Pix, and so on. To understand these complex applications, you will take different real-world data sets and put them to use. Prof. Rowel Atienza discusses the intuition behind deep learning, advances in GANs & techniques to create cutting edge AI- models Now there is a Deepfake that can animate your face with just your voice and a picture using temporal GANs Now there’s a CycleGAN to visualize the effects of climate change. But is this enough to mobilize action?

Despite Facebook’s frequent appearance in the news for all the wrong reasons, we cannot deny that its open source contributions to AI have been its one redeeming quality. At its F8 annual developer conference showcasing its exceptional AI prowess, Facebook shared how the production-ready PyTorch 1.0 is being adopted by the community and also the release of PyTorch 1.1. Facebook introduced PyTorch in 2017, and since then it has been well-received by developers. It partnered with the AI community for further development in PyTorch and released the stable version last year in December. Along with optimizing and fixing other parts of PyTorch, the team introduced Just-in-time compilation for production support that allows seamless transitions between eager mode and graph mode. PyTorch 1.0 in leading businesses, communities, and universities Facebook is leveraging end-to-end workflows of PyTorch 1.0 for building and deploying translation and NLP at large scale. These NLP systems are delivering a staggering 6 billion translations for applications such as Messenger. PyTorch has also enabled Facebook to quickly iterate their ML systems. It has helped them accelerate their research-to-production cycle. Other leading organizations and businesses are also now using PyTorch for speeding up the development of AI features. Airbnb’s Smart Reply feature is backed by PyTorch libraries and APIs for conversational AI. ATOM (Accelerating Therapeutics for Opportunities in Medicine) has come up with a variational autoencoder that represents diverse chemical structures and designs new drug candidates. Microsoft has built large-scale distributed language models that are now in production in offerings such as Cognitive Services. PyTorch 1.1 releases with new model understanding and visualization tools Along with showcasing how the production-ready version is being accepted by the community, the PyTorch team further announced the release of PyTorch 1.1. This release focuses on improved performance, brings new model understanding and visualization tools for improved usability, and more. Following are some of the key feature PyTorch 1.1 comes with: Support for TensorBoard: TensorBoard, a suite of visualization tools, is now natively supported in PyTorch. You can use it through the  “from torch.utils.tensorboard import SummaryWriter” command. Improved JIT compiler: Along with some bug fixes, the team has expanded capabilities in TorchScript such as support for dictionaries, user classes, and attributes. Introducing new APIs: New APIs are introduced to support Boolean tensors and custom recurrent neural networks. Distributed training: This release comes with improved performance for common models such as CNNs. Multi-device modules support and the ability to split models across GPUs while still using Distributed Data Parallel is added. Ax, BoTorch, and more: Open source tools for Machine Learning engineers Facebook announced that it is open sourcing two new tools, Ax and BoTorch that are aimed at solving large scale exploration problems both in research and production environment. Built on top of PyTorch, BoTorch leverages its features such as auto-differentiation, massive parallelism, and deep learning to help in researches related Bayesian optimization. Ax is a general purpose ML platform for managing adaptive experiments. Both Ax and BoTorch use probabilistic models that efficiently use data and meaningfully quantify the costs and benefits of exploring new regions of problem space. Facebook has also open sourced PyTorch-BigGraph (PBG), a tool that makes it easier and faster to produce graph embeddings for extremely large graphs with billions of entities and trillions of edges. PBG comes with support for sharding and negative sampling and also offers sample use cases based on Wikidata embedding. As a result of its collaboration with Google, AI Platform Notebooks, a new histed JupyterLab service from Google Cloud Platform, now comes preinstalled with PyTorch. It also comes integrated with other GCP services such as BigQuery, Cloud Dataproc, Cloud Dataflow, and AI Factory. The broader PyTorch community has also come up with some impressive open source tools. BigGAN-Torch is basically a full reimplementation of PyTorch that uses gradient accumulation to provide the benefits of big batches by only using a few GPUs. GeomLoss is an API written in Python that defines PyTorch layers for geometric loss functions between sampled measures, images, and volumes. It provides efficient GPU implementations for Kernel norms, Hausdorff divergences, and unbiased Sinkhorn divergences. PyTorch Geometric is a geometric deep learning extension library for PyTorch consisting of various methods for deep learning on graphs and other irregular structures. Read the official announcement on Facebook’s AI  blog. Facebook open-sources F14 algorithm for faster and memory-efficient hash tables “Is it actually possible to have a free and fair election ever again?,” Pulitzer finalist, Carole Cadwalladr on Facebook’s role in Brexit F8 Developer Conference Highlights: Redesigned FB5 app, Messenger update, new Oculus Quest and Rift S, Instagram shops, and more

Ethics is, without a doubt, one of the most important topics to emerge in machine learning and artificial intelligence over the last year. While the reasons for this are complex, it nevertheless underlines that the area has reached technological maturity. After all, if artificial intelligence systems weren’t having a real, demonstrable impact on wider society, why would anyone be worried about its ethical implications? It’s easy to dismiss the debate around machine learning and artificial intelligence as abstract and irrelevant to engineers’ and developers’ immediate practical concerns. However this is wrong. Ethics needs to be seen as an important practical consideration for anyone using and building machine learning systems. If we fail to do so the consequences could be serious. The last 12 months has been packed with stories of artificial intelligence not only showing theoretical bias, but also causing discriminatory outcomes in the real world. Amazon scrapped its AI tool for hiring last October because it showed significant bias against female job applicants. Even more recently, last month it emerged that algorithms built to detect hate speech online have in-built biases against black people. Although these might seem like edge cases, it’s vital that everyone in the industry takes responsibility. This isn’t something we can leave up to regulation or other organizations the people who can really affect change are the developers and engineers on the ground. It’s true that machine learning and artificial intelligence systems will be operating in ways where ethics isn’t really an issue - and that’s fine. But by focusing on machine learning ethics, and thinking carefully about the impact of your work you will ultimately end up building better systems that are more robust and have better outcomes. So with that in mind, let’s look at the practical ways to start thinking about ethics in machine learning and artificial intelligence. Machine learning ethics and bias The first step towards thinking seriously about ethics in machine learning is to think about bias. Once you are aware of how bias can creep into machine learning systems, and how that can have ethical implications, it becomes much easier to identify issues and make changes - or, even better, stop them before they arise. Bias isn’t strictly an ethical issue. It could be a performance issue that’s affecting the effectiveness of your system. But in the conversation around AI and machine learning ethics, it’s the most practical way of starting to think seriously about the issue. Types of machine learning and algorithmic bias Although there are a range of different types of bias, the best place to begin is with two top level concepts. You may have read lists of numerous different biases, but for the purpose of talking about ethics there are two important things to think about. Pre-existing and data set biases Pre-existing biases are embedded in the data on which we choose to train algorithms. While it’s true that just about every data set will be ‘biased’ in some way (data is a representation, after all - there will always be something ‘missing), the point here is that we need to be aware of the extent of the bias and the potential algorithmic consequences. You might have heard terms like ‘sampling bias’, ‘exclusion bias’ and ‘prejudice bias’ - these aren’t radically different. They all result from pre-existing biases about how a data set looks or what it represents. Technical and contextual biases Technical machine learning bias is about how an algorithm is programmed. It refers to the problems that arise when an algorithm is built to operate in a specific way. Essentially, it occurs when the programmed elements of an algorithm fail to properly account for the context in which it is being used. A good example is the plagiarism checker Turnitin - this used an algorithm that was trained to identify strings of texts, which meant it would target non-native English speakers over English speaking ones, who were able to make changes to avoid detection. Although there are, as I’ve said, many different biases in the field of machine learning, by thinking about the data on which your algorithm is trained and the context in which the system is working, you will be in a much better place to think about the ethical implications of your work. Equally, you will also be building better systems that don’t cause unforeseen issues. Read next: How to learn data science: from data mining to machine learning The importance of context in machine learning The most important thing for anyone working in machine learning and artificial intelligence is context. Put another way, you need to have a clear sense of why you are trying to do something and what the possible implications could be. If this is unclear, think about it this way: when you use an algorithm, you’re essentially automating away decision making. That’s a good thing when you want to make lots of decisions at a huge scale. But the one thing you lose when turning decision making into a mathematical formula is context. The decisions an algorithm makes lack context because it is programmed to react in a very specific way. This means contextual awareness is your problem. That’s part of the bargain of using an algorithm. Context in data collection Let’s look at what thinking about context means when it comes to your data set. Step 1: what are you trying to achieve? Essentially, the first thing you’ll want to consider is what you’re trying to achieve. Do you want to train an algorithm to recognise faces? Do you want it to understand language in some way? Step 2: why are you doing this? What’s the point of doing what you’re doing? Sometimes this might be a straightforward answer, but be cautious if the answer is too easy to answer. Making something work more efficiently or faster isn’t really a satisfactory reason. What’s the point of making something more efficient? This is often where you’ll start to see ethical issues emerge more clearly. Sometimes they’re not easily resolved. You might not even be in a position to resolve them yourself (if you’re employed by a company, after all, you’re quite literally contracted to perform a specific task). But even if you do feel like there’s little room to maneuver, it’s important to ensure that these discussions actually take place and that you consider the impact of an algorithm. That will make it easier for you to put safeguarding steps in place. Step 3: Understanding the data set Think about how your data set fits alongside the what and the why. Is there anything missing? How was the data collected? Could it be biased or skewed in some way? Indeed, it might not even matter. But if it does, it’s essential that you pay close attention to the data you’re using. It’s worth recording any potential limitations or issues, so if a problem arises at a later stage in your machine learning project, the causes are documented and visible to others. The context of algorithm implementation The other aspect of thinking about context is to think carefully about how your machine learning or artificial intelligence system is being implemented. Is it working how you thought it would? Is it showing any signs of bias? Many articles about the limitations of artificial intelligence and machine learning ethics cite the case of Microsoft’s Tay. Tay was a chatbot that ‘learned’ from its interactions with users on Twitter. Built with considerable naivety, Twitter users turned Tay racist in a matter of days. Users ‘spoke’ to Tay using racist language, and because Tay learned through interactions with Twitter users, the chatbot quickly became a reflection of the language and attitudes of those around it. This is a good example of how the algorithm’s designers didn’t consider how the real-world implementation of the algorithm would have a negative consequence. Despite, you’d think, the best of intentions, the developers didn’t have the foresight to consider the reality of the world into which they were releasing their algorithmic progeny. Read next: Data science vs. machine learning: understanding the difference and what it means today Algorithmic impact assessments It’s true that ethics isn’t always going to be an urgent issue for engineers. But in certain domains, it’s going to be crucial, particularly in public services and other aspects of government, like justice. Maybe there should be a debate about whether artificial intelligence and machine learning should be used in those contexts at all. But if we can’t have that debate, at the very least we can have tools that help us to think about the ethical implications of the machine learning systems we build. This is where Algorithmic Impact Assessments come in. The idea was developed by the AI Now institute and outlined in a paper published last year, and was recently implemented by the Canadian government. There’s no one way to do an algorithmic impact assessment - the Canadian government uses a questionnaire “designed to help you assess and mitigate the risks associated with deploying an automated decision system.” This essentially provides a framework for those using and building algorithms to understand the scope of their project and to identify any potential issues or problems that could arise. Tools for assessing bias and supporting ethical engineering However, although algorithmic impact assessments can provide you with a solid conceptual grounding for thinking about the ethical implications of artificial intelligence and machine learning systems, there are also a number of tools that can help you better understand the ways in which algorithms could be perpetuating biases or prejudices. One of these is FairML, “an end-to- end toolbox for auditing predictive models by quantifying the relative significance of the model's inputs” - helping engineers to identify the extent to which algorithmic inputs could cause harm or bias - while another is LIME (Local Interpretable Model Agnostic Explanations). LIME is not dissimilar to FairML. it aims to understand why an algorithm makes the decisions it does by ‘perturbing’ inputs and seeing how this affects its outputs. There’s also Deon, which is a lot like a more lightweight, developer-friendly version of an algorithmic assessment impact. It’s a command line tool that allows you to add an ethics checklist to your projects. All these tools underline some of the most important elements in the fight for machine learning ethics. FairML and LIME are both attempting to make interpretability easier, while Deon is making it possible for engineers to bring a holistic and critical approach directly into their day to day work. It aims to promote transparency and improve communication between engineers and others. The future of artificial intelligence and machine learning depends on developers taking responsibility Machine learning and artificial intelligence are hitting maturity. They’re technologies that are now, after decades incubated in computer science departments and military intelligence organizations, transforming and having an impact in a truly impressive range of domains. With this maturity comes more responsibility. Ethical questions arise as machine learning affects change everywhere, spilling out into everything from marketing to justice systems. If we can’t get machine learning ethics right, then we’ll never properly leverage the benefits of artificial intelligence and machine learning. People won’t trust it and legislation will start to severely curb what it can do. It’s only by taking responsibility for its effects and consequences that we can be sure it will not only have a transformative impact on the world, but also one that’s safe and for the benefit of everyone.

Alphabet, Google’s parent company, saw its stock price rise quickly after it announced its Q2 2018 earning results, shocking analysts (in a good way) all over the world. Shares of Alphabet have jumped more than 5% in after-hours trading Monday, hitting a new record high. Source: NASDAQ It would seem that the EU’s fine of €4.34 billion on Google for breaching EU antitrust laws had little effect on its progress in terms of Q2 earnings. According to Ruth Porat, Google's CFO, Alphabet generated revenue of $32.66 billion during Q2 2018, compared to $26.01 billion during the same quarter last year. Excluding the fine, Alphabet still booked a net income of $3.2 billion, which equals earnings of $4.54 per share. Had the EU decision gone the other way, Alphabet would have had $32.6 billion in revenue and a profit of $8.2 billion. “We want Google to be the source you think of when you run into a problem.” - Sundar Pichai, Google CEO, in the Q2 2018 Earnings Call In Monday afternoon’s earnings call, CEO Sundar Pichai focused on three major domains that have helped Alphabet achieve its Q2 earnings. First, he claimed that machine learning and AI was becoming a crucial unifying component across all of Google's products and offerings helping to cement and consolidate its position in the market. Second, Pichai suggested that investments in computing, video, cloud and advertising platforms have helped push Google into new valuable markets. And third, the company's investment in new businesses and emerging markets was proving to be a real growth driver which should secure Google's future success. Let us look at the various facets of Google’s growth strategy that have proven to be successful this quarter. Investing in AI With the world spinning around the axis of AI, Alphabet is empowering all of its product and service offerings with AI and machine learning. At its annual developer conference earlier this year, Google I/O, Google announced new updates to their products that rely on machine learning. For example, the revamped Google news app uses machine learning to provide relevant news stories for users, and improvements to Google assistant also helped the organization strengthen its position in that particular market. (By the end of 2018, it will be available in more than 30 languages in 80 countries.) This is another smart move by Alphabet in its plan to make information accessible to all while generating more revenue-generating options for themselves and expanding their partnerships to new vendors and enterprise clients. Google Translate also saw a huge bump in volume especially during the World Cup, as fans all over the world traveled to Russia to witness the football gala. Another smart decision was adding updates to Google Maps. This has achieved a 50% year-on-year growth in Indonesia, India, and Nigeria, three very big and expanding markets. Defending its Android ecosystem and business model The first Android Phone arrived in 2008. The project was built on the simple idea of a mobile platform that was free and open to everyone. Today, there are more than 24,000 Android-powered devices from over 1400 phone manufacturers. Google’s decision to build a business model that encourages this open ecosystem to thrive has been a clever strategy. It not only generates significant revenue for the company but it also brings a world of developers and businesses into its ecosystem. It's vendor lock-in with a friendly face. Of course, with the EU watching closely, Google has to be careful to follow regulation. Failure to comply could mean the company would face penalty payments of up to 5% of its average daily worldwide turnover of Alphabet. According to Brian Wieser, an analyst at Pivotal Research Group, however, “There do not appear to be any signs that should cause a meaningful slow down anytime soon, as fines from the EU are not likely to hamper Alphabet’s growth rate. Conversely, regulatory changes such as GDPR in Europe (and similar laws implemented elsewhere) could have the effect of reinforcing Alphabet’s growth.” Forming new partnerships Google has always been very keen to form new partnerships and strategic alliances with a wide variety of companies and startups. It has been very smart in systematically looking for partners that will complement their strengths and bring the end product to the market. Partnering also provides flexibility; instead of developing new solutions and tools in-house, Google can instead bring interesting innovations into the Google ecosystem simply thanks to its financial clout. For example, Google has partnered with many electronic companies to expand the number of devices compatible with Google assistant. Furthermore, its investment in computing platforms and AI has also helped the organization to generate considerable momentum in their Made by Google hardware business across Pixel, Home, Nest, and Chromecast. Interestingly, we also saw an acceleration in business adoption of Chromebooks. Chromebooks are the most cost-efficient and secure way for businesses to enable their employees to work in the cloud. The unit sales of managed Chromebooks in Q2 grew by more than 175% year-on-year. “Advertising on Youtube has always been an incredibly strong and growing source of income for its creators. Now Google is also building new ways for creators to source income such as paid channel memberships, merchandise shelves on Youtube channels, and endorsements opportunities through Famebit.”, said Pichai. Famebit is a startup they acquired in 2016 which uses data analytics to build tools to connect brands with the right creators. This acquisition proved to be quite successful as almost half of the creators that used Famebit in 2018 doubled their revenue in the first 3 months. Google has also made significant strides in developing new shopping and commerce partnerships such as with leading global retailers like Carrefour, designed to give people the power to shop wherever and however they want. Such collaborations are great for Google as it brings their shopping, ads, and cloud products under one hood. The success of Google Cloud’s vertical strategy and customer-centric approach was illustrated by key wins including Domino's Pizza, Soundcloud, and PwC moving to GCP this quarter. Target, the chain of department store retailers in the US, is also migrating key areas of it’s business to GCP. AirAsia has also expanded its relationship with Google for using ML and data analytics. This shows that the cloud business is only going to grow further. Further, Google Cloud Platform catering to clients from across very different industries and domains signals a robust way to expand their cloud empire. Supporting future customers Google is not just thinking about its current customer base but also working on specialized products to support the next wave of people which are coming online for the first time, enabled the rise in accessibility of mobile devices. They have established high-speed public WiFi in 400 train stations in India in collaboration with the Indian railways and proposed the system in Indonesia and Mexico as well. They have also announced Google AI research center in Ghana Africa to spur AI innovation with researchers and engineers from Africa. They have also expanded the Google IT support professional certificate program to more than 25 community colleges in the US. This massive uproar by Alphabet even in the midst of EU antitrust case was the most talked about news among Wall Street analysts. Most of them consider it to be buy-in terms of stocks. For the next quarter, Google wants to continue fueling its growing cloud business “We are investing for the long run.” Pichai said. They also don’t plan to dramatically alter their Android strategy and continue to give the OS for free. Pichai said, “I’m confident that we will find a way to make sure Android is available at scale to users everywhere.” A quick look at E.U.’s antitrust case against Google’s Android Is Google planning to replace Android with Project Fuchsia? Google Cloud Launches Blockchain Toolkit to help developers build apps easily

What is a convolutional neural network, exactly? Well, let's start with the basics: a convolutional neural network (CNN) is a type of neural network that is most often applied to image processing problems. You've probably seen them in action anywhere a computer is identifying objects in an image. But you can also use convolutional neural networks in natural language processing projects, too. The fact that they are useful for these fast growing areas is one of the main reasons they're so important in deep learning and artificial intelligence today. What makes a convolutional neural network unique? Once you understand how a convolutional neural network works and what makes it unique from other neural networks, you can see why they're so effective for processing and classifying images. But let’s first take a regular neural network. A regular neural network has an input layer, hidden layers and an output layer. The input layer accepts inputs in different forms, while the hidden layers perform calculations on these inputs. The output layer then delivers the outcome of the calculations and extractions. Each of these layers contains neurons that are connected to neurons in the previous layer, and each neuron has its own weight. This means you aren’t making any assumptions about the data being fed into the network - great usually, but not if you’re working with images or language. Convolutional neural networks work differently as they treat data as spatial. Instead of neurons being connected to every neuron in the previous layer, they are instead only connected to neurons close to it and all have the same weight. This simplification in the connections means the network upholds the spatial aspect of the data set. It means your network doesn’t think an eye is all over the image. The word ‘convolutional’ refers to the filtering process that happens in this type of network. Think of it this way, an image is complex - a convolutional neural network simplifies it so it can be better processed and ‘understood.’ What's inside a convolutional neural network? Like a normal neural network, a convolutional neural network is made up of multiple layers. There are a couple of layers that make it unique - the convolutional layer and the pooling layer. However, like other neural networks, it will also have a ReLu or rectified linear unit layer, and a fully connected layer. The ReLu layer acts as an activation function, ensuring non-linearity as the data moves through each layer in the network - without it, the data being fed into each layer would lose the dimensionality that we want to maintain. The fully connected layer, meanwhile, allows you to perform classification on your dataset. The convolutional layer The convolutional layer is the most important, so let’s start there. It works by placing a filter over an array of image pixels - this then creates what’s called a convolved feature map. "It’s a bit like looking at an image through a window which allows you to identify specific features you might not otherwise be able to see. The pooling layer Next we have the pooling layer - this downsamples or reduces the sample size of a particular feature map. This also makes processing much faster as it reduces the number of parameters the network needs to process. The output of this is a pooled feature map. There are two ways of doing this, max pooling, which takes the maximum input of a particular convolved feature, or average pooling, which simply takes the average. These steps amount to feature extraction, whereby the network builds up a picture of the image data according to its own mathematical rules. If you want to perform classification, you'll need to move into the fully connected layer. To do this, you'll need to flatten things out - remember, a neural network with a more complex set of connections can only process linear data. How to train a convolutional neural network There are a number of ways you can train a convolutional neural network. If you’re working with unlabelled data, you can use unsupervised learning methods. One of the best popular ways of doing this is using auto-encoders - this allows you to squeeze data in a space with low dimensions, performing calculations in the first part of the convolutional neural network. Once this is done you’ll then need to reconstruct with additional layers that upsample the data you have. Another option is to use generative adversarial networks, or GANs. With a GAN, you train two networks. The first gives you artificial data samples that should resemble data in the training set, while the second is a ‘discriminative network’ - it should distinguish between the artificial and the 'true' model. What's the difference between a convolutional neural network and a recurrent neural network? Although there's a lot of confusion about the difference between a convolutional neural network and a recurrent neural network, it's actually more simple than many people realise. Whereas a convolutional neural network is a feedforward network that filters spatial data, a recurrent neural network, as the name implies, feeds data back into itself. From this perspective recurrent neural networks are better suited to sequential data. Think of it like this: a convolutional network is able to perceive patterns across space - a recurrent neural network can see them over time. How to get started with convolutional neural networks If you want to get started with convolutional neural networks Python and TensorFlow are great tools to begin with. It’s worth exploring MNIST dataset too. This is a database of handwritten digits that you can use to get started with building your first convolutional neural network. To learn more about convolutional neural networks, artificial intelligence, and deep learning, visit Packt's store for eBooks and videos.

DeepMind, a London based artificial intelligence (AI) company currently owned by Alphabet, recently made great strides in AI with its AlphaGo program. It all began in October 2015 when the program beat the European Go champion Fan Hui 5-0, in a game of Go. This was the very first time an AI defeated a professional Go player. Earlier, computers were only known to have played Go at the "amateur" level. Then, the company made headlines again in 2016 after its AlphaGo program beat Lee Sedol, a professional Go player (a world champion) with a score of 4-1 in a five-game match. Furthermore, in late 2017, an improved version of the program called AlphaGo Zero defeated AlphaGo 100 games to 0. The best part? AlphaGo Zero's strategies were self-taught i.e it was trained without any data from human games. AlphaGo Zero was able to defeat its predecessor in only three days time with lesser processing power than AlphaGo. However, the original AlphaGo, on the other hand required months to learn how to play. All these facts beg the questions: what makes AlphaGo Zero so exceptional? Why is it such a big deal? How does it even work? So, without further ado, let’s dive into the what, why, and how of DeepMind’s AlphaGo Zero. What is DeepMind AlphaGo Zero? Simply put, AlphaGo Zero is the strongest Go program in the world (with the exception of AlphaZero). As mentioned before, it monumentally outperforms all previous versions of AlphaGo. Just check out the graph below which compares the Elo rating of the different versions of AlphaGo. Source: DeepMind The Elo rating system is a method for calculating the relative skill levels of players in zero-sum games such as chess and Go. It is named after its creator Arpad Elo, a Hungarian-American physics professor. Now, all previous versions of AlphaGo were trained using human data. The previous versions learned and improved upon the moves played by human experts/professional Go players. But AlphaGo Zero didn’t use any human data whatsoever. Instead, it had to learn completely from playing against itself. According to DeepMind's Professor David Silver, the reason that playing against itself enables it to do so much better than using strong human data is that AlphaGo always has an opponent of just the right level. So it starts off extremely naive, with perfectly random play. And yet at every step of the learning process, it has an opponent (a “sparring partner”) that’s exactly calibrated to its current level of performance. That is, to begin with, these players are terribly weak but over time they become progressively stronger and stronger. Why is reinforcement learning such a big deal? People tend to assume that machine learning is all about big data and massive amounts of computation. But actually, with AlphaGo Zero, AI scientists at DeepMind realized that algorithms matter much more than the computing processing power or data availability. AlphaGo Zero required less computation than previous versions and yet it was able to perform at a much higher level due to using much more principled algorithms than before. It is a system which is trained completely from scratch, starting from random behavior, and progressing from first principles to really discover tabula rasa, in playing the game of Go. It is, therefore, no longer constrained by the limits of human knowledge. Note that AlphaGo Zero did not use zero-shot learning which essentially is the ability of the machine to solve a task despite not having received any training for that task. How does it work? AlphaGo Zero is able to achieve all this by employing a novel form of reinforcement learning, in which AlphaGo Zero becomes its own teacher. As explained previously, the system starts off with a single neural network that knows absolutely nothing about the game of Go. By combining this neural network with a powerful search algorithm, it then plays games against itself. As it plays more and more games, the neural network is updated and tuned to predict moves, and even the eventual winner of the games. This revised neural network is then recombined with the search algorithm to generate a new, stronger version of AlphaGo Zero, and the process repeats. With each iteration, the performance of the system enhances with each iteration, and the quality of the self-play games’ advances, leading to increasingly accurate neural networks and ever-more powerful versions of AlphaGo Zero. Now, let’s dive into some of the technical details that make this version of AlphaGo so much better than all its forerunners. AlphaGo Zero's neural network was trained using TensorFlow, with 64 GPU workers and 19 CPU parameter servers. Only four Tensor Processing Units (TPUs) were used for inference. And of course, the neural network initially knew nothing about Go beyond the rules. Both AlphaGo and AlphaGo Zero took a general approach to play Go. Both evaluated the Go board and chose moves using a combination of two methods: Conducting a “lookahead” search: This means looking ahead several moves by simulating games, and hence seeing which current move is most likely to lead to a “good” position in the future. Assessing positions based on an “intuition” of whether a position is “good” or “bad”  and is likely to result in a win or a loss. Go is a truly intricate game which means computers can’t merely search all possible moves using a brute force approach to discover the best one. Method 1: Lookahead Before AlphaGo, all the finest Go programs tackled this issue by using “Monte Carlo Tree Search” or MCTS. This process involves initially exploring numerous possible moves on the board and then focusing this search over time as certain moves are found to be more likely to result in wins than others. Source: LOC Both AlphaGo and AlphaGo Zero apply a fairly elementary version of MCTS for their “lookahead” to correctly maintain the tradeoff between exploring new sequences of moves or more deeply explore already-explored sequences. Although MCTS has been at the heart of all effective Go programs preceding AlphaGo, it was DeepMind’s smart coalescence of this method with a neural network-based “intuition” that enabled it to attain superhuman performance. Method 2: Intuition DeepMind’s pivotal innovation with AlphaGo was to utilize deep neural networks to identify the state of the game and then use this knowledge to effectively guide the search of the MCTS. In particular, they trained networks that could record: The current board position Which player was playing The sequence of recent moves (in order to rule out certain moves as “illegal”) With this data, the neural networks could propose: Which move should be played If the current player is likely to win or not So how did DeepMind train neural networks to do this? Well, AlphaGo and AlphaGo Zero used rather different approaches in this case. AlphaGo had two separately trained neural networks: Policy Network and Value Network. Source: AlphaGo’s Nature Paper DeepMind then fused these two neural networks with MCTS  —  that is, the program’s “intuition” with its brute force “lookahead” search — in an ingenious way. It used the network that had been trained to predict: Moves to guide which branches of the game tree to search Whether a position was “winning” to assess the positions it encountered during its search This let AlphaGo to intelligently search imminent moves and eventually beat the world champion Lee Sedol. AlphaGo Zero, however, took this principle to the next level. Its neural network’s “intuition” was trained entirely differently from that of AlphaGo. More specifically: The neural network was trained to play moves that exhibited the improved evaluations from performing the “lookahead” search The neural network was tweaked so that it was more likely to play moves like those that led to wins and less likely to play moves similar to those that led to losses during the self-play games Much was made of the fact that no games between humans were used to train AlphaGo Zero. Thus, for a given state of a Go agent, it can constantly be made smarter by performing MCTS-based lookahead and using the results of that lookahead to upgrade the agent. This is how AlphaGo Zero was able to perpetually improve, from when it was an “amateur” all the way up to when it better than the best human players. Moreover, AlphaGo Zero’s neural network architecture can be referred to as a “two-headed” architecture. Source: Hacker Noon Its first 20 layers were “blocks” of a typically seen in modern neural net architectures. These layers were followed by two “heads”: One head that took the output of the first 20 layers and presented probabilities of the Go agent making certain moves Another head that took the output of the first 20 layers and generated a probability of the current player winning. What’s more, AlphaGo Zero used a more “state of the art” neural network architecture as opposed to AlphaGo. Particularly, it used a “residual” neural network architecture rather than a plainly “convolutional” architecture. Deep residual learning was pioneered by Microsoft Research in late 2015, right around the time work on the first version of AlphaGo would have been concluded. So, it is quite reasonable that DeepMind did not use them in the initial AlphaGo program. Notably, each of these two neural network-related acts —  switching from separate-convolutional to the more advanced dual-residual architecture and using the “two-headed” neural network architecture instead of separate neural networks  —  would have resulted in nearly half of the increase in playing strength as was realized when both were coupled. Source: AlphaGo’s Nature Paper Wrapping it up According to DeepMind: “After just three days of self-play training, AlphaGo Zero emphatically defeated the previously published version of AlphaGo - which had itself defeated 18-time world champion Lee Sedol - by 100 games to 0. After 40 days of self-training, AlphaGo Zero became even stronger, outperforming the version of AlphaGo known as “Master”, which has defeated the world's best players and world number one Ke Jie. Over the course of millions of AlphaGo vs AlphaGo games, the system progressively learned the game of Go from scratch, accumulating thousands of years of human knowledge during a period of just a few days. AlphaGo Zero also discovered new knowledge, developing unconventional strategies and creative new moves that echoed and surpassed the novel techniques it played in the games against Lee Sedol and Ke Jie.” Further, the founder and CEO of DeepMind, Dr. Demis Hassabis believes AlphaGo's algorithms are likely to most benefit to areas that need an intelligent search through an immense space of possibilities. Author Bio Gaurav is a Senior SEO and Content Marketing Analyst at The 20 Media, a Content Marketing agency that specializes in data-driven SEO. He has more than seven years of experience in Digital Marketing and along with that loves to read and write about AI, Machine Learning, Data Science and much more about the emerging technologies. In his spare time, he enjoys watching movies and listening to music. Connect with him on Twitter and LinkedIn. DeepMind researchers provide theoretical analysis on recommender system, ‘echo chamber’ and ‘filter bubble effect’ What if AIs could collaborate using human-like values? DeepMind researchers propose a Hanabi platform. Google DeepMind’s AI AlphaStar beats StarCraft II pros TLO and MaNa; wins 10-1 against the gamers  

No discussion on image processing can be complete without talking about OpenCV. Its 2500+ algorithms, extensive documentation and sample code are considered world-class for exploring real-time computer vision. OpenCV supports a wide variety of programming languages such as C++, Python, Java, etc., and is also available on different platforms including Windows, Linux, OS X, Android, and iOS. OpenCV-Python, the Python API for OpenCV is one of the most popular libraries used to solve computer vision problems. It combines the best qualities of OpenCV, C++ API, and the Python language. The OpenCV-Python library uses Numpy, which is a highly optimized library for numerical operations with a MATLAB-style syntax. This makes it easier to integrate the Python API with other libraries that use Numpy such as SciPy and Matplotlib. This is the reason why it is used by many developers to execute different computer vision experiments. Want to know more about OpenCV with Python? [box type="shadow" align="" class="" width=""]If you are interested in developing your computer vision skills, you should definitely master the algorithms in OpenCV 4 and Python explained in our book ‘Mastering OpenCV 4 with Python’ written by Alberto Fernández Villán. This book will help you build complete projects in relation to image processing, motion detection, image segmentation, and many other tasks by exploring the deep learning Python libraries and also by learning the OpenCV deep learning capabilities.[/box] At the PyData Warsaw 2018 conference, Sylwek Brzęczkowski walked through how to implement a face swap using OpenCV and Python. Face swaps are used by apps like Snapchat to dispense various face filters. Brzęczkowski is a Python developer at TrustStamp. Steps to implement face swapping with OpenCV and Python #1 Face detection using histogram of oriented gradients (HOG) Histogram of oriented gradients (HOG) is a feature descriptor that is used to detect objects in computer vision and image processing. Brzęczkowski demonstrated the working of a HOG using square patches which when hovered over an array of images produces a histogram of oriented gradients feature vectors. These feature vectors are then passed to the classifier to generate a result having the highest matching samples. In order to implement face detection using HOG in Python, the image needs to be imported using import OpenCV. Next a frontal face detector object is created for the loaded image detector=dlib.get_frontal_face_detector(). The detector then produces the vector with the detected face. #2 Facial landmark detection aka face alignment Face landmark detection is the process of finding points of interest in an image of a human face. When dlib is used for facial landmark detection, it returns 68 unique fashion landmarks for the whole face. After the first iteration of the algorithm, the value of T equals 0. This value increases linearly such that at the end of the iteration, T gets the value 10. The image evolved at this stage produces the ‘ground truth’, which means that the iteration can stop now. Due to this working, this stage of the process is also called as face alignment. To implement this stage, Brzęczkowski showed how to add a predictor in the Python program with the values shape_predictor_68_face_landmarks.dat such that it produces a model of around 100 megabytes. This process generally takes up a long time as we tend to pick the biggest clearer image for detection. #3 Finding face border using convex hull The convex hull is a set of points defined as the smallest convex polygon, which encloses all of the points in the set. This means that for a given set of points, the convex hull is the subset of these points such that all the given points are inside the subset. To find the face border in an image, we need to change the structure a bit. The structure is first passed to the convex hull function with return points to false, this means that we get an output of indexes. Brzęczkowski then exhibited the face border in the image in blue color using the find_convex_hull.py function. #4 Approximating nonlinear operations with linear operations In a linear filtering of an image, the value of an output pixel is a linear combination of the values of the pixels. Brzęczkowski put forth the example of Affine transformation which is a type of linear mapping method and is used to preserve points, straight lines, and planes. On the other hand, a non-linear filtering produces an output which is not a linear function of its input. He then goes on to unveil both the transitions using his own image. Brzęczkowski then advised users to check the website learnOpenCV.com to learn how to create a nonlinear operation with a linear one. #5 Finding triangles in an image using Delaunay triangulation A Delaunay triangulation subdivides a set of points in a plane into triangles such that the points become vertices of the triangles. This means that this method subdivides the space or the surface into triangles in such a way that if you look at any triangle on the image, it will not have another point inside the triangle. Brzęczkowski then demonstrates how the image developed in the previous stage contained “face points from which you can identify my teeth and then create sub div to the object, insert all these points that I created or all detected.” Next, he deploys Delaunay triangulation to produce a list of two angles. This list is then used to obtain the triangles in the image. Post this step, he uses the delaunay_triangulation.py function to generate these triangles on the images. #6 Blending one face into another To recap, we started from detecting a face using HOG and finding its border using convex hull, followed it by adding mouth points to indicate specific indexes. Next, Delaunay triangulation was implemented to obtain all the triangles on the images. Next, Brzęczkowski begins the blending of images using seamless cloning. A seamless cloning combines the attributes of other cloning methods to create a unique solution to allow “sequence-independent and scarless insertion of one or more fragments of DNA into a plasmid vector.” This cloning method also provides a variety of skin colors to choose from. Brzęczkowski then explains a feature called ‘pass on edit image’ in the Poisson image editing which uses the value of the gradients instead of the identities or the values of the pixels of the image. To implement the same method in OpenCV, he further demonstrates how information like source, destination, source image destination, mask and center (which is the location where the cloned part should be placed) is required to blend the two faces. Brzęczkowski then depicts a  string of illustrations to transform his image with the images of popular artists like Jamie Foxx, Clint Eastwood, and others. #7 Stabilization using optical flow with the Lucas-Kanade method In computer vision, the Lucas-Kanade method is a widely used differential method for optical flow estimation. It assumes that the flow is essentially constant in a local neighborhood of the pixel under consideration, and solves the basic optical flow equations for all the pixels in that neighborhood, by the least-squares criterion. Thus by combining information from several nearby pixels, the Lucas–Kanade method resolves the inherent ambiguity of the optical flow equation. This method is also less sensitive to noises in an image. By using this method to implement the stabilization of the face swapped image, it is assumed that the optical flow is essentially constant in a local neighborhood of the pixel under consideration in human language. This means that “if we have a red point in the center we assume that all the points around, let's say in this example is three on three pixels we assume that all of them have the same optical flow and thanks to that assumption we have nine equations and only two unknowns.” This makes the computation fairly easy to solve. By using this assumption the optical flow works smoothly if we have the previous gray position of the image. This means that for face swapping images using OpenCV, a user needs to have details of the previous points of the image along with the current points of the image. By combining all this information, the actual point becomes a combination of the detected landmark and the predicted landmark. Thus by implementing the Lucas-Kanade method for stabilizing the image, Brzęczkowski implements a non-shaky version of his face-swapped image. Watch Brzęczkowski’s full video to see a step-by-step implementation of a face-swapping task. You can learn advanced applications like facial recognition, target tracking, or augmented reality from our book, ‘Mastering OpenCV 4 with Python’ written by Alberto Fernández Villán. This book will also help you understand the application of artificial intelligence and deep learning techniques using popular Python libraries like TensorFlow and Keras. Getting to know PyMC3, a probabilistic programming framework for Bayesian Analysis in Python How to perform exception handling in Python with ‘try, catch and finally’ Implementing color and shape-based object detection and tracking with OpenCV and CUDA [Tutorial] OpenCV 4.0 releases with experimental Vulcan, G-API module and QR-code detector among others

[box type="info" align="" class="" width=""]We are happy to bring you an elegant guest post on ensemble methods by Benjamin Rogojan, popularly known as The Seattle Data Guy.[/box] How do data scientists improve their algorithm’s accuracy or improve the robustness of a model? A method that is tried and tested is ensemble learning. It is a must know topic if you claim to be a data scientist and/or a machine learning engineer. Especially, if you are planning to go in for a data science/machine learning interview. Essentially, ensemble learning stays true to the meaning of the word ‘ensemble’. Rather than having several people who are singing at different octaves to create one beautiful harmony (each voice filling in the void of the other), ensemble learning uses hundreds to thousands of models of the same algorithm that work together to find the correct classification. Another way to think about ensemble learning is the fable of the blind men and the elephant. Each blind man in the story seeks to identify the elephant in front of them. However, they work separately and come up with their own conclusions about the animal. Had they worked in unison, they might have been able to eventually figure out what they were looking at. Similarly, ensemble learning utilizes the workings of different algorithms and combines them for a successful and optimal classification. Ensemble methods such as Boosting and Bagging have led to an increased robustness of statistical models with decreased variance. Before we begin with explaining the various ensemble methods, let us have a glance at the common bond between them, Bootstrapping. Bootstrap: The common glue Explaining Bootstrapping can occasionally be missed by many data scientists. However, an understanding of bootstrapping is essential as both the ensemble methods, Boosting and Bagging, are based on the concept of bootstrapping. Figure 1: Bootstrapping In machine learning terms, bootstrap method refers to random sampling with replacement. This sample, after replacement, is referred as a resample. This allows the model or algorithm to get a better understanding of the various biases, variances, and features that exist in the resample. Taking a sample of the data allows the resample to contain different characteristics which the sample might have contained. This would, in turn, affect the overall mean, standard deviation, and other descriptive metrics of a data set. Ultimately, leading to the development of more robust models. The above diagram depicts each sample population having different and non-identical pieces. Bootstrapping is also great for small size data sets that may have a tendency to overfit. In fact, we recommended this to one company who was concerned because their data sets were far from “Big Data”. Bootstrapping can be a solution in this case because algorithms that utilize bootstrapping are more robust and can handle new datasets depending on the methodology chosen (boosting or bagging). The bootstrap method can also test the stability of a solution. By using multiple sample data sets and then testing multiple models, it can increase robustness.  In certain cases, one sample data set may have a larger mean than another or a different standard deviation. This might break a model that was overfitted and not tested using data sets with different variations. One of the many reasons bootstrapping has become so common is because of the increase in computing power. This allows multiple permutations to be done with different resamples. Let us now move on to the most prominent ensemble methods: Bagging and Boosting. Ensemble Method 1: Bagging Bagging actually refers to Bootstrap Aggregators. Most papers or posts that explain bagging algorithms are bound to refer to Leo Breiman’s work, a paper published in 1996 called  “Bagging Predictors”. In the paper, Leo describes bagging as: “Bagging predictors is a method for generating multiple versions of a predictor and using these to get an aggregated predictor.” Bagging helps reduce variance from models that are accurate only on the data they were trained on. This problem is also known as overfitting. Overfitting happens when a function fits the data too well. Typically this is because the actual equation is highly complicated to take into account each data point and the outlier. Figure 2: Overfitting Another example of an algorithm that can overfit easily is a decision tree. The models that are developed using decision trees require very simple heuristics. Decision trees are composed of a set of if-else statements done in a specific order. Thus, if the data set is changed to a new data set that might have some bias or difference in the spread of underlying features compared to the previous set, the model will fail to be as accurate as before. This is because the data will not fit the model well. Bagging gets around the overfitting problem by creating its own variance amongst the data. This is done by sampling and replacing data while it tests multiple hypotheses (models). In turn, this reduces the noise by utilizing multiple samples that would most likely be made up of data with various attributes (median, average, etc). Once each model has developed a hypothesis, the models use voting for classification or averaging for regression. This is where the “Aggregating” of the “Bootstrap Aggregating” comes into play. As in the figure shown below, each hypothesis has the same weight as all the others. (When we later discuss boosting, this is one of the places the two methodologies differ.) Figure 3: Bagging Essentially, all these models run at the same time and vote on the hypothesis which is the most accurate. This helps to decrease variance i.e. reduce the overfit. Ensemble Method 2: Boosting Boosting refers to a group of algorithms that utilize weighted averages to make weak learners into stronger learners. Unlike bagging (that has each model run independently and then aggregate the outputs at the end without preference to any model), boosting is all about “teamwork”. Each model that runs dictates what features the next model will focus on. Boosting also requires bootstrapping. However, there is another difference here. Unlike bagging, boosting weights each sample of data. This means some samples will be run more often than others. Why put weights on the samples of data? Figure 4: Boosting When boosting runs each model, it tracks which data samples are the most successful and which are not. The data sets with the most misclassified outputs are given heavier weights. This is because such data sets are considered to have more complexity. Thus, more iterations would be required to properly train the model. During the actual classification stage, boosting tracks the model's error rates to ensure that better models are given better weights. That way, when the “voting” occurs, like in bagging, the models with better outcomes have a stronger pull on the final output. Which of these ensemble methods is right for me? Ensemble methods generally out-perform a single model. This is why many Kaggle winners have utilized ensemble methodologies. Another important ensemble methodology, not discussed here, is stacking. Boosting and bagging are both great techniques to decrease variance. However, they won’t fix every problem, and they themselves have their own issues. There are different reasons why you would use one over the other. Bagging is great for decreasing variance when a model is overfitted. However, boosting is likely to be a better pick of the two methods. This is because it is also great for decreasing bias in an underfit model. On the other hand, boosting is likely to suffer performance issues. This is where experience and subject matter expertise comes in! It may seem easy to jump on the first model that works. However, it is important to analyze the algorithm and all the features it selects. For instance, a decision tree that sets specific leafs shouldn’t be implemented if it can’t be supported with other data points and visuals. It is not just about trying AdaBoost, or Random forests on various datasets. The final algorithm is driven depending on the results an algorithm is getting and the support provided. [author title="About the Author"] Benjamin Rogojan Ben has spent his career focused on healthcare data. He has focused on developing algorithms to detect fraud, reduce patient readmission and redesign insurance provider policy to help reduce the overall cost of healthcare. He has also helped develop analytics for marketing and IT operations in order to optimize limited resources such as employees and budget. Ben privately consults on data science and engineering problems both solo as well as with a company called Acheron Analytics. He has experience both working hands-on with technical problems as well as helping leadership teams develop strategies to maximize their data.[/author]

TensorFlow 2.0 was released recently with tighter integration with Keras, eager execution enabled by default, three times faster training performance, a cleaned-up API, and more.  TensorFlow 2.0 had a major API Cleanup. Many API symbols are removed or renamed for better consistency and clarity. It now enables eager execution by default which effectively means that your TensorFlow code runs like numpy code. Keras has been introduced as the main high-level API to enable developers to easily leverage Keras’ various model-building APIs. TensorFlow 2.0 also has the SavedModel API that allows you to save your trained Machine learning model into a language-neutral format.  In May, Paige Bailey, Product Manager (TensorFlow) and Laurence Moroney,  Developer Advocate at Google sat down to discuss frequently asked questions on TensorFlow 2.0. They talked about TensorFlow prebuilt binaries, the TF 2.0 upgrade script, Tensorflow Datasets, and Python support. Can I ask about any prebuilt binary for the RTX 2080 GPU on Ubuntu 16?  Prebuilt binaries for TensorFlow tend to be associated with a specific driver from Nvidia. If you're taking a look at any of the prebuilt binaries, take a look at what driver or what version of the driver you have supported on that specific card. It's easy for you to go to the driver vendor and download the latest version. But that may not be the one that TensorFlow is built for or the one that it supports. So, just make sure that they actually match each other.  Do my TensorFlow scripts work with TensorFlow 2.0?  Generally, TensorFlow scripts do not work with TensorFlow 2.0. But TensorFlow 2.0 has created an upgrade utility that is automatically downloaded with TensorFlow 2.0. For more information, you can check out this medium blog post that Paige and her colleague Anna created. It shows how you can upgrade script on an end file - any arbitrary Python file or even Jupyter Notebooks. It'll give you an export.txt file that shows you all of the symbol renames, the added keywords, and then some manual changes.  When will TensorFlow be supported in Python 3.7 and hence be accessed in Anaconda 3? TensorFlow has made the commitment that as of January 1, 2020, they no longer support Python 2. They are firmly committed to Python 3 and Python 3 support.  Is it possible to run Tensorboard on colabs? You can run Tensorboard on colabs and do different operations like smoothing, changing some of the values, and using the embedding visualizer directly from your collab notebook in order to understand accuracies and to be able to model performance debugging. You also don't have to specify ports which means you need not remember to have multiple tensor board instances running. Tensorboard automatically selects one that would be a good candidate.  How would you use [TensorFlow’s] feature_columns with Keras? TensorFlow's feature_columns API is quite useful for non-numerical feature processing. Feature columns are a way of getting your data efficiently into Estimators and you can use them in Keras. TensorFlow 2.0 also has a migration guide if you wanted to migrate your models from using Estimators to being more of a TensorFlow 2.0 format with Keras.   What are some simple data sets for testing and comparing different training methods for artificial neural networks? Are there any in TensorFlow 2.0? Although MNIST and Fashion-MNIST are great, TensorFlow 2.0 also has TensorFlow Datasets which provide a collection of datasets ready to use with TensorFlow. It handles downloading and preparing the data and constructing a tf.data. TensorFlow Datasets is compatible with both TensorFlow Eager mode and Graph mode. Also, you can use them with all of your deep learning and machine learning models with just a few lines of code.  What about all the web developers who are new to AI, how does TensorFlow 2.0 help them get started? With TensorFlow 2.0, the web models that you create using saved model can be deployed to TFLite, or TensorFlow.js. The Keras layers are also supported in TensorFlow.js, so it's not just for Python developers but also for JS developers or even R developers.  You can watch Paige and Lawrence answering more questions in this three-part video series available on YouTube. Some of the other  questions asked were: Is there any TensorFlow.js transfer learning example for object detection? Are you going to publish the updated version of TensorFlow from Poets tutorial from Pete Warden implementing TF2.0. TFLite 2.0 and NN-API for faster inference on Android devices equipped with NPU/DSP? Will the frozen graph generated from TF 1.x work on TF 2.0? Which is the preferred format for saving the model GOIU forward saved_model (SM) or hd5? What is the purpose of keeping Estimators and Keras as separate APIs?  If you want to quickly start with building machine learning projects with TensorFlow 2.0, read our book TensorFlow 2.0 Quick Start Guide by Tony Holdroyd. In this book, you will get acquainted with some new practices introduced in TensorFlow 2.0. You will also learn to train your own models for effective prediction, using high-level Keras API.  TensorFlow.js contributor Kai Sasaki on how TensorFlow.js eases web-based machine learning application development Introducing Spleeter, a Tensorflow based python library that extracts voice and sound from any music track. TensorFlow 2.0 released with tighter Keras integration, eager execution enabled by default, and more! Brad Miro talks TensorFlow 2.0 features and how Google is using it internally

Scientific Computing relies on executing computer algorithms coded in different programming languages. One such interdisciplinary scientific field is the study of Computer Vision, often abbreviated as CV. Computer Vision is used to develop techniques that can automate tasks like acquiring, processing, analyzing and understanding digital images. It is also utilized for extracting high-dimensional data from the real world to produce symbolic information. In simple words, Computer Vision gives computers the ability to see, understand and process images and videos like humans. The vast advances in hardware, machine learning tools, and frameworks have resulted in the implementation of Computer Vision in various fields like IoT, manufacturing, healthcare, security, etc. Major tech firms like Amazon, Google, Microsoft, and Facebook are investing immensely in the research and development of this field. Out of the many tools and libraries available for Computer Vision nowadays, there are two major tools OpenCV and Matlab that stand out in terms of their speed and efficiency. In this article, we will have a detailed look at both of them. Further Reading [box type="shadow" align="" class="" width=""]To learn how to build interesting image recognition models like setting up license plate recognition using OpenCV, read the book “Computer Vision Projects with OpenCV and Python 3” by author Matthew Rever. The book will also guide you to design and develop production-grade Computer Vision projects by tackling real-world problems.[/box] OpenCV: An open-source multiplatform solution tailored for Computer Vision OpenCV, developed by Intel and now supported by Willow Garage, is released under the BSD 3-Clause license and is free for commercial use. It is one of the most popular computer vision tools aimed at providing a well-optimized, well tested, and open-source (C++)-based implementation for computer vision algorithms. The open-source library has interfaces for multiple languages like C++, Python, and Java and supports Linux, macOS, Windows, iOS, and Android. Many of its functions are implemented on GPU. The first stable release of OpenCV version 1.0 was in the year 2006. The OpenCV community has grown rapidly ever since and with its latest release, OpenCV version 4.1.1, it also brings improvements in the dnn (Deep Neural Networks) module, which is a popular module in the library that implements forward pass (inferencing) with deep networks, which are pre-trained using popular deep learning frameworks.  Some of the features offered by OpenCV include: imread function to read the images in the BGR (Blue-Green-Red) format by default. Easy up and downscaling for resizing an image. Supports various interpolation and downsampling methods like INTER_NEAREST to represent the nearest neighbor interpolation. Supports multiple variations of thresholding like adaptive thresholding, bitwise operations, edge detection, image filtering, image contours, and more. Enables image segmentation (Watershed Algorithm) to classify each pixel in an image to a particular class of background and foreground. Enables multiple feature-matching algorithms, like brute force matching, knn feature matching, among others. With its active community and regular updates for Machine Learning, OpenCV is only going to grow by leaps and bounds in the field of Computer Vision projects.  MATLAB: A licensed quick prototyping tool with OpenCV integration One disadvantage of OpenCV, which makes novice computer vision users tilt towards Matlab is the former's complex nature. OpenCV is comparatively harder to learn due to lack of documentation and error handling codes. Matlab, developed by MathWorks is a proprietary programming language with a multi-paradigm numerical computing environment. It has over 3 million users worldwide and is considered one of the easiest and most productive software for engineers and scientists. It has a very powerful and swift matrix library.  Matlab also works in integration with OpenCV. This enables MATLAB users to explore, analyze, and debug designs that incorporate OpenCV algorithms. The support package of MATLAB includes the data type conversions necessary for MATLAB and OpenCV. MathWorks provided Computer Vision Toolbox renders algorithms, functions, and apps for designing and testing computer vision, 3D vision, and video processing systems. It also allows detection, tracking, feature extraction, and matching of objects. Matlab can also train custom object detectors using deep learning and machine learning algorithms such as YOLO v2, Faster R-CNN, and ACF. Most of the toolbox algorithms in Matlab support C/C++ code generation for integrating with existing code, desktop prototyping, and embedded vision system deployment. However, Matlab does not contain as many functions for computer vision as OpenCV, which has more of its functions implemented on GPU. Another issue with Matlab is that it's not open-source, it’s license is costly and the programs are not portable.  Another important factor which matters a lot in computer vision is the performance of a code, especially when working on real-time video processing.  Which has a faster execution time? OpenCV or Matlab? Along with Computer Vision, other fields also require faster execution while choosing a programming language or library for implementing any function. This factor is analyzed in detail in a paper titled “Matlab vs. OpenCV: A Comparative Study of Different Machine Learning Algorithms”.  The paper provides a very practical comparative study between Matlab and OpenCV using 20 different real datasets. The differentiation is based on the execution time for various machine learning algorithms like Classification and Regression Trees (CART), Naive Bayes, Boosting, Random Forest and K-Nearest Neighbor (KNN). The experiments were run on an Intel core 2 duo P7450 machine, with 3GB RAM, and Ubuntu 11.04 32-bit operating system on Matlab version 7.12.0.635 (R2011a), and OpenCV C++ version 2.1.  The paper states, “To compare the speed of Matlab and OpenCV for a particular machine learning algorithm, we run the algorithm 1000 times and take the average of the execution times. Averaging over 1000 experiments is more than necessary since convergence is reached after a few hundred.” The outcome of all the experiments revealed that though Matlab is a successful scientific computing environment, it is outrun by OpenCV for almost all the experiments when their execution time is considered. The paper points out that this could be due to a combination of a number of dimensionalities, sample size, and the use of training sets. One of the listed machine learning algorithms KNN produced a log time ratio of 0.8 and 0.9 on datasets D16 and D17 respectively.  Clearly, Matlab is great for exploring and fiddling with computer vision concepts as researchers and students at universities that can afford the software. However, when it comes to building production-ready real-world computer vision projects, OpenCV beats Matlab hand down. You can learn about building more Computer Vision projects like human pose estimation using TensorFlow from our book ‘Computer Vision Projects with OpenCV and Python 3’. Master the art of face swapping with OpenCV and Python by Sylwek Brzęczkowski, developer at TrustStamp NVIDIA releases Kaolin, a PyTorch library to accelerate research in 3D computer vision and AI Generating automated image captions using NLP and computer vision [Tutorial] Computer vision is growing quickly. Here’s why. Introducing Intel’s OpenVINO computer vision toolkit for edge computing

The Canadian Parliament's Standing Committee on Access to Information, Privacy and Ethics hosted the hearing of the International Grand Committee on Big Data, Privacy and Democracy from Monday, May 27 to Wednesday, May 29.  Witnesses from at least 11 countries appeared before representatives to testify on how governments can protect democracy and citizen rights in the age of big data. This section of the hearing, which took place on May 28, includes Jim Balsillie’s take on Data Governance. Jim Balsillie, Chair, Centre for International Governance Innovation; Retired Chairman and co-CEO of BlackBerry, starts off by talking about how Data governance is the most important public policy issue of our time. It is cross-cutting with economic, social and security dimensions. It requires both national policy frameworks and international coordination. He applauded the seriousness and integrity of Mr. Zimmer Angus and Erskine Smith who have spearheaded a Canadian bipartisan effort to deal with data governance over the past three years. “My perspective is that of a capitalist and global tech entrepreneur for 30 years and counting. I'm the retired Chairman and co-CEO of Research in Motion, a Canadian technology company [that] we scaled from an idea to 20 billion in sales. While most are familiar with the iconic BlackBerry smartphones, ours was actually a platform business that connected tens of millions of users to thousands of consumer and enterprise applications via some 600 cellular carriers in over 150 countries. We understood how to leverage Metcalfe's law of network effects to create a category-defining company, so I'm deeply familiar with multi-sided platform business model strategies as well as navigating the interface between business and public policy.”, he adds. He further talks about his different observations about the nature, scale, and breadth of some collective challenges for the committee’s consideration: Disinformation in fake news is just two of the negative outcomes of unregulated attention based business models. They cannot be addressed in isolation; they have to be tackled horizontally as part of an integrated whole. To agonize over social media’s role in the proliferation of online hate, conspiracy theories, politically motivated misinformation, and harassment, is to miss the root and scale of the problem. Social media’s toxicity is not a bug, it's a feature. Technology works exactly as designed. Technology products services and networks are not built in a vacuum. Usage patterns drive product development decisions. Behavioral scientists involved with today's platforms helped design user experiences that capitalize on negative reactions because they produce far more engagement than positive reactions. Among the many valuable insights provided by whistleblowers inside the tech industry is this quote, “the dynamics of the attention economy are structurally set up to undermine the human will.” Democracy and markets work when people can make choices align with their interests. The online advertisement driven business model subverts choice and represents a fundamental threat to markets election integrity and democracy itself. Technology gets its power through the control of data. Data at the micro-personal level gives technology unprecedented power to influence. “Data is not the new oil, it's the new plutonium amazingly powerful dangerous when it spreads difficult to clean up and with serious consequences when improperly used.” Data deployed through next-generation 5G networks are transforming passive in infrastructure into veritable digital nervous systems. Our current domestic and global institutions rules and regulatory frameworks are not designed to deal with any of these emerging challenges. Because cyberspace knows no natural borders, digital transformation effects cannot be hermetically sealed within national boundaries; international coordination is critical. With these observations, Balsillie has further provided six recommendations: Eliminate tax deductibility of specific categories of online ads. Ban personalized online advertising for elections. Implement strict data governance regulations for political parties. Provide effective whistleblower protections. Add explicit personal liability alongside corporate responsibility to effect the CEO and board of directors’ decision-making. Create a new institution for like-minded nations to address digital cooperation and stability. Technology is becoming the new 4th Estate Technology is disrupting governance and if left unchecked could render liberal democracy obsolete. By displacing the print and broadcast media and influencing public opinion, technology is becoming the new Fourth Estate. In our system of checks and balances, this makes technology co-equal with the executive that led the legislative and the judiciary. When this new Fourth Estate declines to appear before this committee, as Silicon Valley executives are currently doing, it is symbolically asserting this aspirational co-equal status. But is asserting the status and claiming its privileges without the traditions, disciplines, legitimacy, or transparency that checked the power of the traditional Fourth Estate. The work of this international grand committee is a vital first step towards reset redress of this untenable current situation. Referring to what Professor Zuboff said last night, we Canadians are currently in a historic battle for the future of our democracy with a charade called sidewalk Toronto. He concludes by saying, “I'm here to tell you that we will win that battle.” To know more you can listen to the full hearing video titled, “Meeting No. 152 ETHI - Standing Committee on Access to Information, Privacy, and Ethics” on ParlVU. Speech2Face: A neural network that “imagines” faces from hearing voices. Is it too soon to worry about ethnic profiling? UK lawmakers to social media: “You’re accessories to radicalization, accessories to crimes”, hearing on spread of extremist content Key Takeaways from Sundar Pichai’s Congress hearing over user data, political bias, and Project Dragonfly

It’s easy to fall into the trap of thinking about your next job, or even the job after that. It’s far more useful, however, to think more about the skills you want and need to learn now. This will focus your mind and ensure that you don’t waste time learning things that simply aren’t helpful. It also means you can make use of the things you’re learning almost immediately. This will make you more productive and effective - and who knows, maybe it will make the pathway to your future that little bit clearer. So, to help you focus, here are some of the things you should focus on learning as a data professional. Reinforcement learning Reinforcement learning is one of the most exciting and cutting-edge areas of machine learning. Although the area itself is relatively broad, the concept itself is fundamentally about getting systems to ‘learn’ through a process of reward. Because reinforcement learning focuses on making the best possible decision at a given moment, it naturally finds many applications where decision making is important. This includes things like robotics, digital ad-bidding, configuring software systems, and even something as prosaic as traffic light control. Of course, the list of potential applications for reinforcement learning could be endless. To a certain extent, the real challenge with it is finding new use cases that are relevant to you. But to do that, you need to learn and master it - so make 2020 the year you do just that. Get to grips with reinforcement learning with Reinforcement Learning Algorithms with Python. Learn neural networks Neural networks are closely related to reinforcement learning - they’re essentially another element within machine learning. However, neural networks are even more closely aligned with what we think of as typical artificial intelligence. Indeed, even the name itself hints at the fact that these systems are supposed to in some way mimic the human brain. Like reinforcement learning, there are a number of different applications for neural networks. These include image and language processing, as well as forecasting. The complexity of relationships that can be figured inside neural networks systems is useful for handling data with many different variables and intricacies that would otherwise be difficult to capture. If you want to find out how artificial intelligence really works under the hood, make sure you learn neural networks in 2020. Learn how to build real-world neural networks projects with Neural Network Projects with Python. Meta-learning Metalearning is another area of machine learning. It’s designed to help engineers and analysts to use the right machine learning algorithms for specific problems - it’s particularly important in automatic machine learning, where removing human agency from the analytical process can lead to the wrong systems being used on data. Meta learning does this by being applied to metadata about machine learning projects. This metadata will include information about the data, such as algorithm features, performance measures, and patterns identified previously. Once meta learning algorithms have ‘learned’ from this data, they should, in theory, be well optimized to run on other sets of data. It has been said that meta learning is important in the move towards generalized artificial intelligence, or AGI (intelligence that is more akin to human intelligence). This is because getting machines to learn about learning allow systems to move between different problems - something that is incredibly difficult with even the most sophisticated neural networks. Whether it will actually get us any closer to AGI is certainly open to debate, but if you want to be a part of the cutting edge of AI development, getting stuck into meta learning is a good place to begin in 2020. Find out how meta learning works in Hands-on Meta Learning with Python. Learn a new programming language Python is now the undisputed language of data. But that’s far from the end of the story - R still remains relevant in the field, and there are even reasons to use other languages for machine learning. It might not be immediately obvious - especially if you’re content to use R or Python for analytics and algorithmic projects - but because machine learning is shifting into many different fields, from mobile development to cybersecurity, learning how other programming languages can be used to build machine learning algorithms could be incredibly valuable. From the perspective of your skill set, it gives you a level of flexibility that will not only help you to solve a wider range of problems, but also stand out from the crowd when it comes to the job market. The most obvious non-obvious languages to learn for machine learning practitioners and other data professionals are Java and Julia. But even new and emerging languages are finding their way into machine learning - Go and Swift, for example, could be interesting routes to explore, particularly if you’re thinking about machine learning in production software and systems. Find out how to use Go for machine learning with Go Machine Learning Projects. Learn new frameworks For data professionals there are probably few things more important than learning new frameworks. While it’s useful to become a polyglot, it’s nevertheless true that learning new frameworks and ecosystem tools are going to have a more immediate impact on your work. PyTorch and TensorFlow should almost certainly be on your list for 2020. But we’ve mentioned them a lot recently, so it’s probably worth highlighting other frameworks worth your focus: Pandas, for data wrangling and manipulation, Apache Kafka, for stream-processing, scikit-learn for machine learning, and Matplotlib for data visualization. The list could be much, much longer: however, the best way to approach learning a new framework is to start with your immediate problems. What’s causing issues? What would you like to be able to do but can’t? What would you like to be able to do faster? Explore TensorFlow eBooks and videos on the Packt store. Learn how to develop and communicate a strategy It’s easy to just roll your eyes when someone talks about how important ‘soft skills’ are for data professionals. Except it’s true - being able to strategize, communicate, and influence, are what mark you out as a great data pro rather than a merely competent one. The phrase ‘soft skills’ is often what puts people off - ironically, despite the name they’re often even more difficult to master than technical skill. This is because, of course, soft skills involve working with humans in all their complexity. However, while learning these sorts of skills can be tough, it doesn’t mean it's impossible. To a certain extent it largely just requires a level of self-awareness and reflexivity, as well as a sensitivity to wider business and organizational problems. A good way of doing this is to step back and think of how problems are defined, and how they relate to other parts of the business. Find out how to deliver impactful data science projects with Managing Data Science. If you can master these skills, you’ll undoubtedly be in a great place to push your career forward as the year continues.

It’s hard to keep up with the pace of change in the data science and machine learning fields. And when you’re under pressure to deliver projects, learning new skills and technologies might be the last thing on your mind. But if you don’t have at least one eye on what you need to learn next you run the risk of falling behind. In turn this means you miss out on new solutions and new opportunities to drive change: you might miss the chance to do things differently. That’s why we want to make it easy for you with this quick list of what you need to watch out for and learn in 2020. The growing TensorFlow ecosystem TensorFlow remains the most popular deep learning framework in the world. With TensorFlow 2.0 the Google-based development team behind it have attempted to rectify a number of issues and improve overall performance. Most notably, some of the problems around usability have been addressed, which should help the project’s continued growth and perhaps even lower the barrier to entry. Relatedly TensorFlow.js is proving that the wider TensorFlow ecosystem is incredibly healthy. It will be interesting to see what projects emerge in 2020 - it might even bring JavaScript web developers into the machine learning fold. Explore Packt's huge range of TensorFlow eBooks and videos on the store. PyTorch PyTorch hasn’t quite managed to topple TensorFlow from its perch, but it’s nevertheless growing quickly. Easier to use and more accessible than TensorFlow, if you want to start building deep learning systems quickly your best bet is probably to get started on PyTorch. Search PyTorch eBooks and videos on the Packt store. End-to-end data analysis on the cloud When it comes to data analysis, one of the most pressing issues is to speed up pipelines. This is, of course, notoriously difficult - even in organizations that do their best to be agile and fast, it’s not uncommon to find that their data is fragmented and diffuse, with little alignment across teams. One of the opportunities for changing this is cloud. When used effectively cloud platforms can dramatically speed up analytics pipelines and make it much easier for data scientists and analysts to deliver insights quickly. This might mean that we need increased collaboration between data professionals, engineers, and architects, but if we’re to really deliver on the data at our disposal, then this shift could be massive. Learn how to perform analytics on the cloud with Cloud Analytics with Microsoft Azure. Data science strategy and leadership While cloud might help to smooth some of the friction that exists in our organizations when it comes to data analytics, there’s no substitute for strong and clear leadership. The split between the engineering side of data and the more scientific or interpretive aspect has been noted, which means that there is going to be a real demand for people that have a strong understanding of what data can do, what it shows, and what it means in terms of action. Indeed, the article just linked to also mentions that there is likely to be an increasing need for executive level understanding. That means data scientists have the opportunity to take a more senior role inside their organizations, by either working closely with execs or even moving up to that level. Learn how to build and manage a data science team and initiative that delivers with Managing Data Science. Going back to the algorithms In the excitement about the opportunities of machine learning and artificial intelligence, it’s possible that we’ve lost sight of some of the fundamentals: the algorithms. Indeed, given the conversation around algorithmic bias, and unintended consequences it certainly makes sense to place renewed attention on the algorithms that lie right at the center of our work. Even if you’re not an experienced data analyst or data scientist, if you’re a beginner it’s just as important to dive deep into algorithms. This will give you a robust foundation for everything else you do. And while statistics and mathematics will feel a long way from the supposed sexiness of data science, carefully considering what role they play will ensure that the models you build are accurate and perform as they should. Get stuck into algorithms with Data Science Algorithms in a Week. Computer vision and natural language processing Computer vision and Natural Language Processing are two of the most exciting aspects of modern machine learning and artificial intelligence. Both can be used for analytics projects, but they also have applications in real world digital products. Indeed, with augmented reality and conversational UI becoming more and more common, businesses need to be thinking very carefully about whether this could give them an edge in how they interact with customers. These sorts of innovations can be driven from many different departments - but technologists and data professionals should be seizing the opportunity to lead the way on how innovation can transform customer relationships. For more technology eBooks and videos to help you prepare for 2020, head to the Packt store.

Machine learning is indeed the tech of present times! Security, which is a growing concern for many organizations today and machine learning is one of the solutions to deal with it. ML can help cybersecurity systems analyze patterns and learn from them to help prevent similar attacks and respond to changing behavior. To know more about machine learning and its application in Cybersecurity, we had a chat with Emmanuel Tsukerman, a Cybersecurity Data Scientist and the author of Machine Learning for Cybersecurity Cookbook. The book also includes modern AI to create powerful cybersecurity solutions for malware, pentesting, social engineering, data privacy, and intrusion detection. In 2017, Tsukerman's anti-ransomware product was listed in the Top 10 ransomware products of 2018 by PC Magazine. In his interview, Emmanuel talked about how ML algorithms help in solving problems related to cybersecurity, and also gave a brief tour through a few chapters of his book. He also touched upon the rise of deepfakes and malware classifiers. On using machine learning for cybersecurity Using Machine learning in Cybersecurity scenarios will enable systems to identify different types of attacks across security layers and also help to take a correct POA. Can you share some examples of the successful use of ML for cybersecurity you have seen recently? A recent and interesting development in cybersecurity is that the bad guys have started to catch up with technology; in particular, they have started utilizing Deepfake tech to commit crime; for example,they have used AI to imitate the voice of a CEO in order to defraud a company of $243,000. On the other hand, the use of ML in malware classifiers is rapidly becoming an industry standard, due to the incredible number of never-before-seen samples (over 15,000,000) that are generated each year. On staying updated with developments in technology to defend against attacks Machine learning technology is not only used by ethical humans, but also by Cybercriminals who use ML for ML-based intrusions. How can organizations counter such scenarios and ensure the safety of confidential organizational/personal data? The main tools that organizations have at their disposal to defend against attacks are to stay current and to pentest. Staying current, of course, requires getting educated on the latest developments in technology and its applications. For example, it’s important to know that hackers can now use AI-based voice imitation to impersonate anyone they would like. This knowledge should be propagated in the organization so that individuals aren’t caught off-guard. The other way to improve one’s security is by performing regular pen tests using the latest attack methodology; be it by attempting to avoid the organization’s antivirus, sending phishing communications, or attempting to infiltrate the network. In all cases, it is important to utilize the most dangerous techniques, which are often ML-based On how ML algorithms and GANs help in solving cybersecurity problems In your book, you have mentioned various algorithms such as clustering, gradient boosting, random forests, and XGBoost. How do these algorithms help in solving problems related to cybersecurity? Unless a machine learning model is limited in some way (e.g., in computation, in time or in training data), there are 5 types of algorithms that have historically performed best: neural networks, tree-based methods, clustering, anomaly detection and reinforcement learning (RL). These are not necessarily disjoint, as one can, for example, perform anomaly detection via neural networks. Nonetheless, to keep it simple, let’s stick to these 5 classes. Neural networks shine with large amounts of data on visual, auditory or textual problems. For that reason, they are used in Deepfakes and their detection, lie detection and speech recognition. Many other applications exist as well. But one of the most interesting applications of neural networks (and deep learning) is in creating data via Generative adversarial networks (GANs). GANs can be used to generate password guesses and evasive malware. For more details, I’ll refer you to the Machine Learning for Cybersecurity Cookbook. The next class of models that perform well are tree-based. These include Random Forests and gradient boosting trees. These perform well on structured data with many features. For example, the PE header of PE files (including malware) can be featurized, yielding ~70 numerical features. It is convenient and effective to construct an XGBoost model (a gradient-boosting model) or a Random Forest model on this data, and the odds are good that performance will be unbeatable by other algorithms. Next there is clustering. Clustering shines when you would like to segment a population automatically. For example, you might have a large collection of malware samples, and you would like to classify them into families. Clustering is a natural choice for this problem. Anomaly detection lets you fight off unseen and unknown threats. For instance, when a hacker utilizes a new tactic to intrude on your network, an anomaly detection algorithm can protect you even if this new tactic has not been documented. Finally, RL algorithms perform well on dynamic problems. The situation can be, for example, a penetration test on a network. The DeepExploit framework, covered in the book, utilizes an RL agent on top of metasploit to learn from prior pen tests and becomes better and better at finding vulnerabilities. Generative Adversarial Networks (GANs) are a popular branch of ML used to train systems against counterfeit data. How can these help in malware detection and safeguarding systems to identify correct intrusion? A good way to think about GANs is as a pair of neural networks, pitted against each other. The loss of one is the objective of the other. As the two networks are trained, each becomes better and better at its job. We can then take whichever side of the “tug of war” battle, separate it from its rival, and use it. In other cases, we might choose to “freeze” one of the networks, meaning that we do not train it, but only use it for scoring. In the case of malware, the book covers how to use MalGAN, which is a GAN for malware evasion. One network, the detector, is frozen. In this case, it is an implementation of MalConv. The other network, the adversarial network, is being trained to modify malware until the detection score of MalConv drops to zero. As it trains, it becomes better and better at this. In a practical situation, we would want to unfreeze both networks. Then we can take the trained detector, and use it as part of our anti-malware solution. We would then be confident knowing that it is very good at detecting evasive malware. The same ideas can be applied in a range of cybersecurity contexts, such as intrusion and deepfakes. On how Machine Learning for Cybersecurity Cookbook can help with easy implementation of ML for Cybersecurity problems What are some of the tools/ recipes mentioned in your book that can help cybersecurity professionals to easily implement machine learning and make it a part of their day-to-day activities? The Machine Learning for Cybersecurity Cookbook offers an astounding 80+ recipes. Themost applicable recipes will vary between individual professionals, and even for each individual different recipes will be applicable at different times in their careers. For a cybersecurity professional beginning to work with malware, the fundamentals chapter, chapter 2:ML-based Malware Detection, provides a solid and excellent start to creating a malware classifier. For more advanced malware analysts, Chapter 3:Advanced Malware Detection will offer more sophisticated and specialized techniques, such as dealing with obfuscation and script malware. Every cybersecurity professional would benefit from getting a firm grasp of chapter 4, “ML for Social Engineering”. In fact, anyone at all should have an understanding of how ML can be used to trick unsuspecting users, as part of their cybersecurity education. This chapter really shows that you have to be cautious because machines are becoming better at imitating humans. On the other hand, ML also provides the tools to know when such an attack is being performed. Chapter 5, “Penetration Testing Using ML” is a technical chapter, and is most appropriate to cybersecurity professionals that are concerned with pen testing. It covers 10 ways in which pen testing can be improved by using ML, including neural network-assisted fuzzing and DeepExploit, a framework that utilizes a reinforcement learning (RL) agent on top of metasploit to perform automatic pen testing. Chapter 6, “Automatic Intrusion Detection” has a wider appeal, as a lot of cybersecurity professionals have to know how to defend a network from intruders. They would benefit from seeing how to leverage ML to stop zero-day attacks on their network. In addition, the chapter covers many other use cases, such as spam filtering, Botnet detection and Insider Threat detection, which are more useful to some than to others. Chapter 7, “Securing and Attacking Data with ML” provides great content to cybersecurity professionals interested in utilizing ML for improving their password security and other forms of data security. Chapter 8, “Secure and Private AI”, is invaluable to data scientists in the field of cybersecurity. Recipes in this chapter include Federated Learning and differential privacy (which allow to train an ML model on clients’ data without compromising their privacy) and testing adversarial robustness (which allows to improve the robustness of ML models to adversarial attacks). Your book talks about using machine learning to generate custom malware to pentest security. Can you elaborate on how this works and why this matters? As a general rule, you want to find out your vulnerabilities before someone else does (who might be up to no-good). For that reason, pen testing has always been an important step in providing security. To pen test your Antivirus well, it is important to use the latest techniques in malware evasion, as the bad guys will certainly try them, and these are deep learning-based techniques for modifying malware. On Emmanuel’s personal achievements in the Cybersecurity domain Dr. Tsukerman, in 2017, your anti-ransomware product was listed in the ‘Top 10 ransomware products of 2018’ by PC Magazine. In your experience, why are ransomware attacks on the rise and what makes an effective anti-ransomware product? Also, in 2018,  you designed an ML-based, instant-verdict malware detection system for Palo Alto Networks' WildFire service of over 30,000 customers. Can you tell us more about this project? If you monitor cybersecurity news, you would see that ransomware continues to be a huge threat. The reason is that ransomware offers cybercriminals an extremely attractive weapon. First, it is very difficult to trace the culprit from the malware or from the crypto wallet address. Second, the payoffs can be massive, be it from hitting the right target (e.g., a HIPAA compliant healthcare organization) or a large number of targets (e.g., all traffic to an e-commerce web page). Thirdly, ransomware is offered as a service, which effectively democratizes it! On the flip side, a lot of the risk of ransomware can be mitigated through common sense tactics. First, backing up one’s data. Second, having an anti-ransomware solution that provides guarantees. A generic antivirus can provide no guarantee - it either catches the ransomware or it doesn’t. If it doesn’t, your data is toast. However, certain anti-ransomware solutions, such as the one I have developed, do offer guarantees (e.g., no more than 0.1% of your files lost). Finally, since millions of new ransomware samples are developed each year, the malware solution must include a machine learning component, to catch the zero-day samples, which is another component of the anti-ransomware solution I developed. The project at Palo Alto Networks is a similar implementation of ML for malware detection. The one difference is that unlike the anti-ransomware service, which is an endpoint security tool, it offers protection services from the cloud. Since Palo Alto Networks is a firewall-service provider, that makes a lot of sense, since ideally, the malicious sample will be stopped at the firewall, and never even reach the endpoint. To learn how to implement the techniques discussed in this interview, grab your copy of the Machine Learning for Cybersecurity Cookbook Don’t wait - the bad guys aren’t waiting. Author Bio Emmanuel Tsukerman graduated from Stanford University and obtained his Ph.D. from UC Berkeley. In 2017, Dr. Tsukerman's anti-ransomware product was listed in the Top 10 ransomware products of 2018 by PC Magazine. In 2018, he designed an ML-based, instant-verdict malware detection system for Palo Alto Networks' WildFire service of over 30,000 customers. In 2019, Dr. Tsukerman launched the first cybersecurity data science course. About the book Machine Learning for Cybersecurity Cookbook will guide you through constructing classifiers and features for malware, which you'll train and test on real samples. You will also learn to build self-learning, reliant systems to handle cybersecurity tasks such as identifying malicious URLs, spam email detection, intrusion detection, network protection, and tracking user and process behavior, and much more! DevSecOps and the shift left in security: how Semmle is supporting software developers [Podcast] Elastic marks its entry in security analytics market with Elastic SIEM and Endgame acquisition Businesses are confident in their cybersecurity efforts, but weaknesses prevail

The huge advancements of deep learning and artificial intelligence were perhaps the biggest story in tech in 2018. But we wanted to know what the future might hold - luckily, we were able to speak to Packt author Will Ballard about what they see as in store for artificial in 2019 and beyond. Will Ballard is the chief technology officer at GLG, responsible for engineering and IT. He was also responsible for the design and operation of large data centers that helped run site services for customers including Gannett, Hearst Magazines, NFL, NPR, The Washington Post, and Whole Foods. He has held leadership roles in software development at NetSolve (now Cisco), NetSpend, and Works (now Bank of America). Explore Will Ballard's Packt titles here. Packt: What do you think the biggest development in deep learning / AI was in 2018? Will Ballard: I think attention models beginning to take the place of recurrent networks is a pretty impressive breakout on the algorithm side. In Packt’s 2018 Skill Up survey, developers across disciplines and job roles identified machine learning as the thing they were most likely to be learning in the coming year. What do you think of that result? Do you think machine learning is becoming a mandatory multidiscipline skill, and why? Almost all of my engineering teams have an active, or a planned machine learning feature on their roadmap. We’ve been able to get all kinds of engineers with different backgrounds to use machine learning -- it really is just another way to make functions -- probabilistic functions -- but functions. What do you think the most important new deep learning/AI technique to learn in 2019 will be, and why? In 2019 -- I think it is going to be all about PyTorch and TensorFlow 2.0, and learning how to host these on cloud PaaS. The benefits of automated machine learning and metalearning How important do you think automated machine learning and metalearning will be to the practice of developing AI/machine learning in 2019? What benefits do you think they will bring? Even ‘simple’ automation techniques like grid search and running multiple different algorithms on the same data are big wins when mastered. There is almost no telling which model is ‘right’ till you try it, so why not let a cloud of computers iterate through scores of algorithms and models to give you the best available answer? Artificial intelligence and ethics Do you think ethical considerations will become more relevant to developing AI/machine learning algorithms going forwards? If yes, how do you think this will be implemented? I think the ethical issues are important on outcomes, and on how models are used, but aren’t the place of algorithms themselves. If a developer was looking to start working with machine learning/AI, what tools and software would you suggest they learn in 2019? Python and PyTorch.