What this book covers

Chapter 1, Keras Installation, covers various installation and setup procedures, as well as defining various Keras configurations.

Chapter 2, Working with Keras Datasets and Models, covers using various datasets, such as CIFAR10, CIFAR100, or MNIST, and many other datasets and models used for image classification. 

Chapter 3, Data Preprocessing, Optimization, and Visualization, covers various preprocessing and optimization techniques using Keras. The optimization techniques covered include TFOptimizer, AdaDelta, and many more.

Chapter 4, Classification Using Different Keras Layers, details various Keras layers, for example, recurrent layers, and convolutional layers. 

Chapter 5, Implementing Convolutional Neural Networks, teaches you convolutional neural network algorithms in detail, using the example of cervical cancer classification and the digit recognition dataset. 

Chapter 6, Generative Adversarial Networks, covers basic generative adversarial networks (GANs) and boundary-seeking GAN.

Chapter 7, Recurrent Neural Networks, covers the basics of recurrent neural networks in order to implement Keras based on historical datasets.

Chapter 8, Natural Language Processing Using Keras Models, covers the basics of NLP for word analysis and sentiment analysis using Keras.

Chapter 9, Text Summarization Using Keras Models, shows you how to use Keras models for text summarization when using the Amazon reviews dataset. 

Chapter 10, Reinforcement Learning, focuses on formulating and developing reinforcement learning models using Keras.