The comprehensive MIT Press book on Deep Learning by Ian Goodfellow, Yoshua Bengio and Aaron Courville, as an initiative to reach and help students as well as professionals to easily start their journey in Machine Learning and Deep Learning.

This book imparts complete knowledge of the subject as it covers basics to advanced topics thoroughly and it will definitely put your search to an end!!

Go grab the book- Deep Learning!

The MIT Deeplearning Book provides a wide range of topics covering important mathematical concepts, deep learning techniques used in industry i.e. it provides a practical approach to work. The book also offers research perspectives, by covering theoretical topics in depth related to data science. After the introduction, this book is divided into 3 sections including a list of subtopics in each as follows.

OUTLINE OF THE BOOK

Part I: Applied Math and Machine Learning Basics

• Linear Algebra

• Probability and Information Theory

• Numerical Computation

• Machine Learning Basics

Part II: Modern Practical Deep Networks

• Deep Feedforward Networks

• Regularization for Deep Learning

• Optimization for Training Deep Models.

• Convolutional Networks

• Sequence Modeling: Recurrent and Recursive Nets

• Practical Methodology

• Applications

Part III: Deep Learning Research

• Linear Factor Models

• Autoencoders

• Representation Learning

• Structured Probabilistic Models for Deep Learning

• Monte Carlo Methods

• Confronting the Partition Function

• Approximate Inference

• Deep Generative Models

This book is definitely a grab for the undergraduates as well as graduate students who are willing to plan their career in either data science industry or research work. Software engineers who want to begin their career in data science can definitely opt for this book.

You can get HTML format for the web version absolutely free of cost from here