Book Image

Keras Deep Learning Cookbook

By : Rajdeep Dua, Sujit Pal, Manpreet Singh Ghotra
Book Image

Keras Deep Learning Cookbook

By: Rajdeep Dua, Sujit Pal, Manpreet Singh Ghotra

Overview of this book

Keras has quickly emerged as a popular deep learning library. Written in Python, it allows you to train convolutional as well as recurrent neural networks with speed and accuracy. The Keras Deep Learning Cookbook shows you how to tackle different problems encountered while training efficient deep learning models, with the help of the popular Keras library. Starting with installing and setting up Keras, the book demonstrates how you can perform deep learning with Keras in the TensorFlow. From loading data to fitting and evaluating your model for optimal performance, you will work through a step-by-step process to tackle every possible problem faced while training deep models. You will implement convolutional and recurrent neural networks, adversarial networks, and more with the help of this handy guide. In addition to this, you will learn how to train these models for real-world image and language processing tasks. By the end of this book, you will have a practical, hands-on understanding of how you can leverage the power of Python and Keras to perform effective deep learning

Related Content you might be interested in

Current Title:

Small book image
Keras Deep Learning Cookbook
Rajdeep Dua | Sujit Pal | Manpreet Singh Ghotra
Oct, 2018 | 252 pages
Small book image
Deep Learning with Keras
Sujit Pal | Antonio Gulli
Apr, 2017 | 318 pages
Small book image
Deep Learning Quick Reference
Michael Bernico
Mar, 2018 | 272 pages
Small book image
Generative Adversarial Networks Cookbook
Josh Kalin
Dec, 2018 | 268 pages
Table of Contents (17 chapters)
Title Page
Title Page
Copyright and Credits
Copyright and Credits
Packt Upsell
Packt Upsell
Contributors
Contributors
Preface
Preface
Free Chapter
1
Keras Installation
Keras Installation
Introduction
Installing Keras on Ubuntu 16.04
Installing Keras with Jupyter Notebook in a Docker image
Installing Keras on Ubuntu 16.04 with GPU enabled
2
Working with Keras Datasets and Models
Working with Keras Datasets and Models
Introduction
CIFAR-10 dataset
CIFAR-100 dataset
MNIST dataset
Load data from a CSV file
Models in Keras – getting started
Sequential models
Shared layer models
Keras functional APIs
Keras functional APIs – linking the layers
Image classification using Keras functional APIs
3
Data Preprocessing, Optimization, and Visualization
Data Preprocessing, Optimization, and Visualization
Feature standardization of image data
Sequence padding
Model visualization
Optimization 
Common code for samples
Optimization with stochastic gradient descent
Optimization with Adam
Optimization with AdaDelta
Optimization with RMSProp
4
Classification Using Different Keras Layers
Classification Using Different Keras Layers
Introduction
Classification for breast cancer
Classification for spam detection
5
Implementing Convolutional Neural Networks
Implementing Convolutional Neural Networks
Introduction
Cervical cancer classification
Digit recognition
6
Generative Adversarial Networks
Generative Adversarial Networks
Introduction
Basic GAN
Boundary seeking GAN
DCGAN
7
Recurrent Neural Networks
Recurrent Neural Networks
Introduction
Simple RNNs for time series data
LSTM networks for time series data
Time series forecasting with LSTM
Sequence to sequence learning for the same length output with LSTM
8
Natural Language Processing Using Keras Models
Natural Language Processing Using Keras Models
Introduction
Word embedding
Sentiment analysis
9
Text Summarization Using Keras Models
Text Summarization Using Keras Models
Introduction
Text summarization for reviews
10
Reinforcement Learning
Reinforcement Learning
Introduction
The CartPole game with Keras
Dueling DQN to play Cartpole 
Other Books You May Enjoy
Other Books You May Enjoy
Leave a review - let other readers know what you think
Index
Index

Introduction

Reinforcement learning is a subset of machine learning, where AI agents learn from the environment by interacting with it and improving their performance. This branch of AI learns by trial and error instead of human supervision. The following diagram illustrates how an AI agent acts on the environment and receives feedback after each action. Feedback is made up of two parts: reward and the next state of the environment. Rewards are defined by a human:

Google's DeepMind published a paper in 2013 about Playing Atari with Deep Reinforcement Learning. In this paper, a new algorithm called Deep Q Network (DQN). It explains how an AI agent can learn to play games by just observing the screen without any prior information about the game. The result of the experiment turned out to be pretty impressive in terms of accuracy. It opened the era of what is called deep reinforcement learning, a mix of deep learning and reinforcement learning.

The Q-Learning algorithm has a function called Q...

Previous Section
End of Section 2
Next Section