An Introduction to Statistical Learning, with Application in R
Gareth James, Daniela Witten, Trevor Hastie, Robert Tibshirani
This is a great book to start learning. It offers a gentle introduction to machine learning guided by examples. It gives little for granted and the mathematical notation is not heavy. It is beginner/medium level. With the “The Elements of Statistical Learning, Data Mining, Inference, and Prediction” offers a complete description of most well-known machine learning methods. It doesn’t discuss about neural networks.
The Elements of Statistical Learning, Data Mining, Inference, and Prediction
Trevor Hastie, Robert Tibshirani, Jerome Friedman
It is the natural continuation of the “An Introduction to Statistical Learning, with Application in R” book. This book is medium/advanced level. It offers more in depth explanation where the introduction book hide some details. The mathematical is sometimes heavy. It does cover neural network in a chapter.
Petter Recognition and Machine Learning
Christopher M. Bishop
This is the bible of all the machine learning books. It starts from the fundamentals to build up. It offers both frequentist and bayesian views of probabilities. The explanations are well discussed and easy to follow.
Deep Learning
Ian Goodfellow, Yoshua Bengio, and Aaron Courville
The books talks about neural networks and most of its variants. It starts from the theory needed to understand all the concepts before diving into neural networks. Given the interest in this topic and the practical applications that use this methods worldwide, it is a book worth read it. Among other, it covers convolutional, recurrent and recursive neural networks.
