Book Image

R Machine Learning Projects

By : Dr. Sunil Kumar Chinnamgari
Book Image

R Machine Learning Projects

By: Dr. Sunil Kumar Chinnamgari

Overview of this book

R is one of the most popular languages when it comes to performing computational statistics (statistical computing) easily and exploring the mathematical side of machine learning. With this book, you will leverage the R ecosystem to build efficient machine learning applications that carry out intelligent tasks within your organization. This book will help you test your knowledge and skills, guiding you on how to build easily through to complex machine learning projects. You will first learn how to build powerful machine learning models with ensembles to predict employee attrition. Next, you’ll implement a joke recommendation engine and learn how to perform sentiment analysis on Amazon reviews. You’ll also explore different clustering techniques to segment customers using wholesale data. In addition to this, the book will get you acquainted with credit card fraud detection using autoencoders, and reinforcement learning to make predictions and win on a casino slot machine. By the end of the book, you will be equipped to confidently perform complex tasks to build research and commercial projects for automated operations.
Table of Contents (12 chapters)
The Road Ahead

Introduction to the MXNet framework

MXNet is a super-powerful open source deep learning framework that is built to ease the development of deep learning algorithms. It is used to define, train, and deploy deep neural networks. MXNet is lean, flexible, and ultra-scalable, that is, it allows fast model training and supports a flexible programming model with multiple languages. The problem with existing deep learning frameworks, such as Torch7, Theano, and Caffe, is that users need to learn another system or a different programming flavor.

However, MXNet resolves this issue by supporting multiple languages, such as C++, Python, R, Julia, and Perl. This eliminates the need for users to learn a new language; therefore, they can use the framework and simplify network definitions. MXNet models are able to fit in small amounts of memory and they can be trained on CPUs, GPUs, and on multiple...