Deep Learning with R Cookbook: Over 45 unique recipes to delve into neural network techniques using R 3.5.x

What do you get with Print?

Instant access to your digital eBook copy whilst your Print order is Shipped

Paperback book shipped to your preferred address

Download this book in EPUB and PDF formats

Access this title in our online reader with advanced features

DRM FREE - Read whenever, wherever and however you want

AI Assistant (beta) to help accelerate your learning

Working with Convolutional Neural Networks

Convolutional Neural Networks (CNNs) are the most popular and widely used deep neural networks for computer vision problems. They are used in a variety of applications including image classification, face recognition, document analysis, medical image analysis, action recognition, and natural language processing. In this chapter, we will focus on learning convolutional operations, and concepts such as padding and strides, to optimize CNNs. The idea behind this chapter is to make you well versed with the functioning of the CNN and learn techniques such as data augmentation and batch normalization to fine-tune your network and prevent overfitting. We will also provide a brief discussion about how we can leverage transfer learning to boost model performance.

In this chapter, we will cover the following recipes:

...

Key benefits

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

Description

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.

Who is this book 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.

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

What do you get with Print?

Instant access to your digital eBook copy whilst your Print order is Shipped

Paperback book shipped to your preferred address

Download this book in EPUB and PDF formats

Access this title in our online reader with advanced features

DRM FREE - Read whenever, wherever and however you want

AI Assistant (beta) to help accelerate your learning

Frequently bought together

AU$60.99

AU$60.99

AU$67.99

Total AU$ 189.97

Karan Bhanot Nov 04, 2020

Disclaimer: One of the coordinators from the Publisher asked me to review this book and sent me a review copy. I promise to be completely honest about my thoughts on this book.Overview:Even though I’ve been working with R for more than a year, this book was my first introduction to deep learning in R (I do have experience in building deep learning models in other languages). This is a great book for anyone who knows about the basics of Deep learning and is looking to use R for developing models and deep learning projects. The book has a wide range of deep learning topics including convolutional neural networks, auto-encoders, NLP etc. The best part is that it explains and then provides the code to do the specific task being talked about which makes following along very easy.Things I like:There are a lot of things that I like about this book. I love how they describe about the various ways to work with deep learning. They discuss about the Tensorflow API, followed by how Microsoft Azure/Google Cloud can be used to do deep learning on the cloud detailing each step to get started and much more.The book is great at elaborating deep learning concepts through practical examples. For instance, the book details about using LSTMs for text generation, uses images to show how computer vision works and also explains how the model is generated. The layers of the model being defined are always highlighted and a section explains each layer used in the model.The authors aptly elaborate on the required theoretical background and explanation of various models. Keep in mind that some basics are required to be known before you can go ahead and understand these models properly.Things I didn’t like:Some of the code blocks are really long and I had trouble following along. Sometimes the code snippets extend beyond a page which makes it a little more troublesome. I quickly found a way around that. They provide a link to their GitHub repository which has all the codes which can be used to follow along in a much easier form.Things I’d like to see:The book can have a couple of chapters with the basics of machine, deep learning and R at the very start, so this book can be extended to complete beginners as well.

Amazon Verified review

Khushboo Oct 09, 2020

To be honest, I have always been a python user. But, being a statistician, I thought it is important to be able to code in R too. After reading and applying concepts of this book, I am sure that it will definitely give you a head start when it comes to design and deploy neural networks algorithm. The flow of a chapter is well designed, starting from understanding the basic concept then move on to how can we implement it. There is a section of "see more" where you can find more useful resources for a particular topic and "Tips" are also very useful to keep in mind. This book covers almost everything you can do with neural nets in R and made my learning task easier as I did not have to make a google search every time I code. Now, I think R is simple to understand compared to Python. :D

Mehrnaz Mar 03, 2021

I like how the book covers different hot topics such as CNN, RNN, reinforcement learning, CV, NLP, ... The other good feature of this book is explaining installation details which is not covered in a lot of books. This is important to me because a lot of books assume that you magically have everything that you need on your computer or you have a cs background, while a lot of people struggle with them. Lastly, going step by step with examples helps to have a better understanding of the concepts.

Deep Learning with R Cookbook: Over 45 unique recipes to delve into neural network techniques using R 3.5.x

What do you get with Print?

Deep Learning with R Cookbook

Working with Convolutional Neural Networks

Introduction to convolutional operations

Understanding strides and padding

Getting familiar with pooling layers

Implementing transfer learning

Getting ready

Page 1 of 5

Key benefits

Description

Who is this book for?

What you will learn

Product Details

What do you get with Print?

Product Details

Frequently bought together

Table of Contents

Recommendations for you

Customer reviews

People who bought this also bought

About the 3 authors

FAQs

Deep Learning with R Cookbook: Over 45 unique recipes to delve into neural network techniques using R 3.5.x

What do you get with Print?

Key benefits

Description

Who is this book for?

What you will learn

Product Details

What do you get with Print?

Product Details

Packt Subscriptions

Frequently bought together

Table of Contents

Recommendations for you

Customer reviews

People who bought this also bought

About the 3 authors

FAQs