Deep learning has taken a huge step in recent years with developments including generative adversarial networks (GANs), variational autoencoders, and deep reinforcement learning. This book serves as a reference guide in R 3.x that will help you implement deep learning techniques.
This book walks you through various deep learning techniques that you can implement in your applications using R 3.x. A unique set of recipes will help you solve regression, binomial classification, and multinomial classification problems, and explores hyper-parameter optimization in detail. You will also go through recipes that implement convolutional neural networks (CNNs), recurrent neural networks (RNNs), long short-term memory (LSTM) networks, sequence-to-sequence models, GANs, and reinforcement learning. You will learn about high-performance computation involving large datasets that utilize GPUs, along with parallel computation capabilities in R, and you will also get familiar with libraries such as MXNet, which is designed for efficient GPU computing and state-of-the-art deep learning. You will also learn how to solve common and not-so-common problems in NLP, such as object detection and action identification, and you will leverage pre-trained models in deep learning applications.
By the end of the book, you will have a logical understanding of deep learning and different deep learning packages and will be able to build the most appropriate solutions to your problems.
