Deep Learning with R Cookbook

Over 45 unique recipes to delve into neural network techniques using R 3.5.x

Swarna Gupta , Rehan Ali Ansari , Dipayan Sarkar 지음

Packt(GCO Science) 2021년 02월 21일 출간

작품소개

책소개

Tackle the complex challenges faced while building end-to-end deep learning models using modern R libraries

▶What You Will Learn
？ Work with different datasets for image classification using CNNs
？ Apply transfer learning to solve complex computer vision problems
？ Use RNNs and their variants such as LSTMs and Gated Recurrent Units (GRUs) for sequence data generation and classification
？ Implement autoencoders for DL tasks such as dimensionality reduction, denoising, and image colorization
？ Build deep generative models to create photorealistic images using GANs and VAEs
？ Use MXNet to accelerate the training of DL models through distributed computing

▶Key Features
？ Understand the intricacies of R deep learning packages to perform a range of deep learning tasks
？ Implement deep learning techniques and algorithms for real-world use cases
？ Explore various state-of-the-art techniques for fine-tuning neural network models

▶Who This Book Is For
>This deep learning book is for data scientists, machine learning practitioners, deep learning researchers and AI enthusiasts who want to learn key tasks in deep learning domains using a recipe-based approach. A strong understanding of machine learning and working knowledge of the R programming language is mandatory.

목차

▶TABLE of CONTENTS
1. Understanding Neural Networks and Deep Neural Networks
2. Working with Convolutional Neural Networks
3. Recurrent Neural Networks in Action
4. Implementing Autoencoders with Keras
5. Deep Generative Models
6. Handling Big Data Using Large-Scale Deep Learning
7. Working with Text and Audio for NLP
8. Deep Learning for Computer Vision
9. Implementing Reinforcement Learning

책 속으로

▶What this book covers
？ Chapter 1, Understanding Neural Networks and Deep Neural Networks, will show us how to set up a deep learning environment to train models. The readers are then introduced to neural networks, starting from how neural networks work, what hidden layers are, what backpropagation is, and what activation functions are. This chapter uses the keras library to demonstrate the recipes.

？ Chapter 2, Working with Convolutional Neural Networks, will show us CNNs and will explain how they can be used to train models for image recognition and natural language processing based tasks. This chapter also covers various hyperparameters and optimizers used with CNNs.

？ Chapter 3, Recurrent Neural Networks in Action, will show us the fundamentals of RNNs with real-life implementation examples. We will also introduce LSTMs and gated recurrent units (GRUs), an extension of RNNs, and take a detailed walk-through of LSTM hyper-parameters. In addition to this, readers will learn how to build a bi-directional RNN model using Keras.

？ Chapter 4, Implementing Autoencoders with Keras, will introduce the implementation of various types of autoencoders using the keras library as the backend. Readers will also learn about various applications of autoencoders, such as dimensionality reduction and image coloring.

？ Chapter 5, Deep Generative Models, will show us the architecture of another method of deep neural networks, generative adversarial networks (GANs). We will demonstrate how to train a GAN model comprising of two pitting nets―a generator and a discriminator. This chapter also covers the practical implementation of variational autoencoders and compares them with GANs.

？ Chapter 6, Handling Big Data Using Large-Scale Deep Learning, contains case studies on highperformance computation involving large datasets utilizing GPUs. Readers will also be introduced to the parallel computation capabilities in R and libraries such as MXNet, which is designed for efficient GPU computing and state-of-the-art deep learning.

？ Chapter 7, Working with Text and Audio for NLP, contains case studies on various topics involving sequence data, including natural language processing (NLP) and speech recognition. The readers will implement end-to-end deep learning algorithms using various deep learning libraries.

？ Chapter 8, Deep Learning for Computer Vision, will provide end-to-end case studies on object detection and face identification.

？ Chapter 9, Implementing Reinforcement Learning, will walk us through the concepts of reinforcement learning step by step. Readers will learn about various methods, such as Markov Decision Processes, Q-Learning, and experience replay, and implement these methods in R using examples. Readers will also implement an end-to-end reinforcement learning example using R packages such as MDPtoolbox and Reinforcementlearning.

출판사 서평

▶ Preface
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.

작가정보

저자(글) Swarna Gupta

Swarna Gupta holds a B.E. in computer science and has 6 years of experience in the data science space. She is currently working with Rolls Royce in the capacity of a data scientist. Her work revolves around leveraging data science and machine learning to create value for the business. She has extensively worked on IoT-based projects in the vehicle telematics and solar manufacturing industries.During her current association with Rolls Royce she worked in various deep learning techniques and solutions to solve fleet issues in aerospace domain. She also manages time from her busy schedule to be a regular pro-bono contributor to social organizations, helping them to solve specific business problems with the help of data science and machine learning.

저자(글) Rehan Ali Ansari

Rehan has a bachelors in Electrical and Electronics engineering with 5 years of experience in data science and machine learning field. He is currently associated with the digital competency at AP Moller Maersk Group in the capacity of a data scientist. He has a diverse background of working in multiple domains like fashion retail, IoT, renewable energy sector and trade finance. He is a strong believer of agile way of developing data driven machine learning and AI products. Out of his busy schedule he manages to explore new areas in the field of AI and robotics.

저자(글) Dipayan Sarkar

Dipayan Sarkar holds a Masters in Economics and comes with 17+ years of experience. Dipayan has won international challenges in predictive modeling and takes a keen interest in the mathematics behind machine learning techniques. Before opting to become an independent consultant and a mentor in the data science and machine learning space with various organizations and educational institutions, he had served in the capacity of a senior data scientist with Fortune 500 companies in the US and Europe. He is currently associated with Great Lakes Institute of Management as a visiting faculty (Analytics) and BML Munjal University as an adjunct faculty (Analytics and Machine Learning). He has co-authored a book on "Ensemble Machine Learning with Python" with PACKT Publishing.