Book Overview & Buying
Table Of Contents

Deep Learning with R Cookbook

By : Gupta, Ansari, Sarkar

5 (3)

Buy this Book

Deep Learning with R Cookbook

5 (3)

By: Gupta, Ansari, Sarkar

Buy this Book

Overview of this book

Deep learning (DL) has evolved in recent years with developments such as generative adversarial networks (GANs), variational autoencoders (VAEs), and deep reinforcement learning. This book will get you up and running with R 3.5.x to help you implement DL techniques. The book starts with the various DL techniques that you can implement in your apps. A unique set of recipes will help you solve binomial and multinomial classification problems, and perform regression and hyperparameter optimization. To help you gain hands-on experience of concepts, the book features recipes for implementing convolutional neural networks (CNNs), recurrent neural networks (RNNs), and Long short-term memory (LSTMs) networks, as well as sequence-to-sequence models and reinforcement learning. You’ll then learn about high-performance computation using GPUs, along with learning about parallel computation capabilities in R. Later, you’ll explore libraries, such as MXNet, that are designed for GPU computing and state-of-the-art DL. Finally, you’ll discover how to solve different problems in NLP, object detection, and action identification, before understanding how to use pre-trained models in DL apps. By the end of this book, you’ll have comprehensive knowledge of DL and DL packages, and be able to develop effective solutions for different DL problems.

Preface

Who this book is for

What this book covers

To get the most out of this book

Sections

Get in touch

Understanding Neural Networks and Deep Neural Networks

Setting up the environment

Implementing neural networks with Keras

Sequential API

Functional API

TensorFlow Estimator API

TensorFlow Core API

Implementing a single-layer neural network

Training your first deep neural network

Free Chapter

Working with Convolutional Neural Networks

Introduction to convolutional operations

Understanding strides and padding

Getting familiar with pooling layers

Implementing transfer learning

Recurrent Neural Networks in Action

Sentiment classification using RNNs

Text generation using LSTMs

Time series forecasting using GRUs

Implementing bidirectional recurrent neural networks

Implementing Autoencoders with Keras

Implementing vanilla autoencoders

Dimensionality reduction using autoencoders

Denoising autoencoders

Changing black and white into color

Deep Generative Models

Generating images with GANs

Implementing DCGANs

Implementing variational autoencoders

Handling Big Data Using Large-Scale Deep Learning

Deep learning on Amazon Web Services

Deep learning on Microsoft Azure

Deep learning on Google Cloud Platform

Accelerating with MXNet

Implementing a deep neural network using MXNet

Forecasting with MXNet

Working with Text and Audio for NLP

Neural machine translation

Summarizing text using deep learning

Speech recognition

Deep Learning for Computer Vision

Object localization

Face recognition

Implementing Reinforcement Learning

Model-based RL using MDPtoolbox

Model-free RL

Cliff walking using RL

Other Books You May Enjoy

Leave a review - let other readers know what you think

Cliff walking using RL

By now, you should be aware of the framework of RL. In this recipe, we will implement a real-world application of the gridworld environment in RL. This problem can be represented as a grid that's 4x12 in size. The episodes start in the lower-left state, with a goal state at the bottom right of the grid. Going left, right, up, and down are the only possible actions at any state. The states labeled C in the lower part of the grid are cliffs. Any transition into these states will incur a high negative reward of -100 and send the agent instantly back to the starting state, S. For the goal state, G, the reward is 0, while it's -1 for all the transitions except the goal state and cliff.

The following image shows the navigation matrix for the cliff walking problem: