Book Image

Deep Learning with Keras

By : Antonio Gulli, Sujit Pal
Book Image

Deep Learning with Keras

By: Antonio Gulli, Sujit Pal

Overview of this book

This book starts by introducing you to supervised learning algorithms such as simple linear regression, the classical multilayer perceptron and more sophisticated deep convolutional networks. You will also explore image processing with recognition of handwritten digit images, classification of images into different categories, and advanced objects recognition with related image annotations. An example of identification of salient points for face detection is also provided. Next you will be introduced to Recurrent Networks, which are optimized for processing sequence data such as text, audio or time series. Following that, you will learn about unsupervised learning algorithms such as Autoencoders and the very popular Generative Adversarial Networks (GANs). You will also explore non-traditional uses of neural networks as Style Transfer. Finally, you will look at reinforcement learning and its application to AI game playing, another popular direction of research and application of neural networks.
Table of Contents (16 chapters)
Title Page
Credits
About the Authors
About the Reviewer
www.PacktPub.com
Customer Feedback
Preface

Keras 2.0 — what is new


According to Francois Chollet, Keras was released two years ago, in March, 2015. It then proceeded to grow from one user to one hundred thousand. The following image, taken from the Keras blog, shows the growth of number of Keras users over time.

One important update with Keras 2.0 is that the API will now be a part of TensorFlow, starting with TensorFlow 1.2. Indeed, Keras is becoming more and more the lingua franca for deep learning, a spec used in an increasing number of deep learning contexts. For instance, Skymind is implementing Keras spec in Scala for ScalNet, and Keras.js is doing the same for JavaScript for running of deep learning directly in the browser. Efforts are also underway to provide a Keras API for MXNET and CNTK deep learning toolkits.

Installing Keras 2.0

Installing Keras 2.0 is very simple via the pip install keras --upgrade followed by pip install tensorflow --upgrade.

API changes

The Keras 2.0 changes implied the need to rethink some APIs. For full...