R Deep Learning Essentials - Second Edition: A step-by-step guide to building deep learning models using TensorFlow, Keras, and MXNet

Implementing neural network models in R 3.5 using TensorFlow, Keras, and MXNet

Key Features

• Use R 3.5 for building deep learning models for computer vision, text and more
• Apply deep learning techniques in the cloud for large-scale processing
• Build, train and optimize neural network models on a range of datasets

Book Description

Deep Learning is a powerful subset of machine learning that is very successful in domains such as computer vision and natural language processing. This book will open the gates for you to enter the world of neural networks by building powerful deep learning models using R ecosystem.

This book will introduce deep learning fundamentals from first principles, you will learn how to build a neural network model from scratch. It will show how to use deep learning libraries such as Keras, MXNet and Tensorflow. We will build deep learning models for a variety of tasks and problems including structured data, computer vision, text data, anomaly detection and recommendation systems. Later we will cover advanced topics such as Generative Adversarial Networks, Transfer Learning, large-scale deep learning in the cloud. You will also learn about the theoretical concepts of deep learning projects such as how to tune and optimize your model, how to deal with overfitting, data augmentation, and other advanced topics.

By the end of this book, you will be all ready to implement deep learning concepts in research work or projects.

What you will learn

• Use deep learning libraries such as Keras, Tensorflow, and MXNet in R
• Build shallow neural network prediction models
• Prevent models from overfitting the data to improve generalizability
• Techniques for finding the best hyperparameters for deep learning models
• Build Natural Language Processing models using Keras and TensorFlow in R
• Learn how to use deep learning for computer vision tasks
• Implement deep learning topics such as GANs, auto-encoders, and transfer learning

Who This Book Is For

This book caters to aspiring data scientists, data analysts, machine learning developers, and deep learning enthusiasts who are well versed in machine learning concepts and are looking to explore the deep learning paradigm using R. You should have a fundamental understanding of the R language to get the most out of the book.