More Information
Learn
  • Understand the main concepts of machine learning and deep learning
  • Install and use Python and Keras to build deep learning models
  • Build, train, and run fully-connected, convolutional and recurrent neural networks
  • Optimize deep neural networks through efficient hyper parameter searches
  • See many real-world applications to identify which tasks can be leveraged with deep learning
  • Work with any kind of data involving images, text, time series, sound and videos
  • Use GPUs to leverage the training experience.
  • Discover some advanced neural architectures such as generative adversarial networks
  • Find out about a wide range of subjects from recommender systems to transfer learning
About

Keras is an open source neural network library written in Python. It is capable of running on top of MXNet, Deeplearning4j, Tensorflow, CNTK, or Theano. Designed to enable fast experimentation with deep neural networks, it focuses on being minimal, modular, and extensible.

This course provides a comprehensive introduction to deep learning. We start by presenting some famous success stories and a brief recap of the most common concepts found in machine learning. Then, we introduce neural networks and the optimization techniques to train them. We’ll show you how to get ready with Keras API to start training deep learning models, both on CPU and on GPU. Then, we present two types of neural architecture: convolutional and recurrent neural networks

First, we present a well-known use case of deep learning: recommender systems, where we try to predict the "rating" or "preference" that a user would give to an item. Then, we introduce an interesting subject called style transfer. Deep learning has this ability to transform images based on a set of inputs, so we’ll morph an image with a style image to combine them into a very realistic result. In the third section, we present techniques to train on very small datasets. This comprises transfer learning, data augmentation, and hyperparameter search, to avoid overfitting and to preserve the generalization property of the network.

Finally, we complete this course by what Yann LeCun, Director at Facebook, considered as the biggest breakthrough in Machine Learning of the last decade: Generative Adversarial Networks. These networks are amazingly good at capturing the underlying distribution of a set of images to generate new images.

Style and Approach

Expect a smooth combination of theory and practice. Code examples illustrate all the important concepts in the course, and you can implement them yourself, guided by the course

Features
  • Recognize whose practical applications can benefit from Deep Learning
  • Get equipped with the knowledge of building, training and using convolutional neural network
  • Solve supervised and unsupervised learning problems using images, text and time series
Course Length 5 hours 11 minutes
ISBN 9781788623957
Date Of Publication 28 Dec 2017

Authors

Philippe Remy

Philippe Remy is a research engineer and entrepreneur working on deep learning and living in Tokyo, Japan.

As a research engineer, Philippe reads scientific papers and implements artificial intelligence algorithms related to handwriting character recognition, time series analysis, and natural language processing.

As an entrepreneur, his vision is to bring a meaningful and transformative impact to society with the ultimate goal of enhancing overall quality of life and pushing the limits of what is considered possible today.

Philippe contributes to different open source projects related to deep learning and fintech (github.com/philipperemy).

You can visit Philippe Remy’s blog on philipperemy.github.io.