Switch to the store?

Practical Convolutional Neural Networks

More Information
Learn
  • From CNN basic building blocks to advanced concepts understand practical areas they can be applied to
  • Build an image classifier CNN model to understand how different components interact with each other, and then learn how to optimize it
  • Learn different algorithms that can be applied to Object Detection, and Instance Segmentation
  • Learn advanced concepts like attention mechanisms for CNN to improve prediction accuracy
  • Understand transfer learning and implement award-winning CNN architectures like AlexNet, VGG, GoogLeNet, ResNet and more
  • Understand the working of generative adversarial networks and how it can create new, unseen images
About

Convolutional Neural Network (CNN) is revolutionizing several application domains such as visual recognition systems, self-driving cars, medical discoveries, innovative eCommerce and more.You will learn to create innovative solutions around image and video analytics to solve complex machine learning and computer vision related problems and implement real-life CNN models.

This book starts with an overview of deep neural networkswith the example of image classification and walks you through building your first CNN for human face detector. We will learn to use concepts like transfer learning with CNN, and Auto-Encoders to build very powerful models, even when not much of supervised training data of labeled images is available.

Later we build upon the learning achieved to build advanced vision related algorithms for object detection, instance segmentation, generative adversarial networks, image captioning, attention mechanisms for vision, and recurrent models for vision.

By the end of this book, you should be ready to implement advanced, effective and efficient CNN models at your professional project or personal initiatives by working on complex image and video datasets.

Features
  • Fast-paced guide with use cases and real-world examples to get well versed with CNN techniques
  • Implement CNN models on image classification, transfer learning, Object Detection, Instance Segmentation, GANs and more
  • Implement powerful use-cases like image captioning, reinforcement learning for hard attention, and recurrent attention models
Page Count 218
Course Length 6 hours 32 minutes
ISBN 9781788392303
Date Of Publication 27 Feb 2018
History of CNNs
Convolutional neural networks
Practical example – image classification
Summary
The differences between object detection and image classification
Traditional, nonCNN approaches to object detection
R-CNN – Regions with CNN features
Fast R-CNN – fast region-based CNN
Faster R-CNN – faster region proposal network-based CNN
Mask R-CNN – Instance segmentation with CNN
Instance segmentation in code
References
Summary

Authors

Md. Rezaul Karim

Md. Rezaul Karim has more than 8 years of experience in the area of research and development with a solid knowledge of algorithms and data structures in C/C++, Java, Scala, R, and Python focusing Big Data technologies: Spark, Kafka, DC/OS, Docker, Mesos, Zeppelin, Hadoop, and MapReduce and Deep Learning technologies: TensorFlow, DeepLearning4j and H2O-Sparking Water. His research interests include Machine Learning, Deep Learning, Semantic Web/Linked Data, Big Data, and Bioinformatics.

He is a Research Scientist at Fraunhofer Institute for Applied Information Technology-FIT, Germany. He is also a Ph.D. candidate at the RWTH Aachen University, Aachen, Germany.

He holds a BS and an MS degree in Computer Engineering. Before joining the Fraunhofer-FIT, he had been working as a Researcher at the Insight Centre for Data Analytics, Ireland. Before that, he worked as a Lead Engineer with Samsung Electronics’ distributed R&D Institutes in Korea, India, Vietnam, Turkey, and Bangladesh.

Before that, he worked as a Research Assistant in the Database Lab at Kyung Hee University, Korea. He also worked as an R&D Engineer with BMTech21 Worldwide, Korea. Even before that, he worked as a Software Engineer with i2SoftTechnology, Dhaka, Bangladesh.

Pradeep Pujari

Pradeep Pujari is a machine learning engineer at Walmart Labs and a distinguished member of ACM. His core domain expertise is in information retrieval, machine learning, and Natural Language Processing. In his free time, he loves exploring AI technologies, reading, and mentoring

Mohit Sewak

Mohit Sewak is an Artificial Intelligence scientist with extensive experience and technical leadership in research, architecture, and solutioning of Artificial Intelligence-driven cognitive and automation products and platforms for industries such as IoT, retail, BFSI, and cyber security.

In his current role at QiO Technologies, Mohit leads the reinforcement learning initiative for Industry 4.0 and Smart IoT.

In his previous role, Mohit was associated with IBM Watson Commerce (Software Group) where he led the research/science initiatives for the Watson Cognitive Commerce line of product features and offerings.

Mohit has been the Lead Data Scientist/Analytics Architect for some of the most renowned industry-leading International AI/ DL/ ML software and industry solutions. Mohit is also a thought leader in the field of Artificial Intelligence and Machine Learning and has authored multiple books and scientific publications in this area..