Return to Answer

##Machine Learning

• One the most, if not the most, popular textbooks on machine learning is Hastie, Tibshirani, and Friedman, The Elements of Statistical Learning, which is fully available online (currently 10th printing). It is comparable in scope e.g. to Bishop's Pattern Recognition and ML or Murphy's ML, but those books are not free, while ESL is.

• Hastie & Tibshirani also co-wrote freely available An Introduction to Statistical Learning, With Applications in R which is basically a simpler version of The Elements and focuses on R.

• In 2015, Hastie & Tibshirani co-authored a new textbook Statistical Learning with Sparsity: The Lasso and Generalizations, also available online. This one is quite a bit shorter and focuses specifically on lasso.

• Another freely available all-encompassing machine learning textbook is David Barber's Bayesian Reasoning and Machine Learning. I did not use it myself, but it is widely considered to be an excellent book.

$\hskip{5em}$

Switching now to more specialized topics, there are:

• Rasmussen & Williams Gaussian Processes for Machine Learning, which is the book on Gaussian processes.

• Much awaited Goodfellow, Bengio and Courville Deep Learning textbook that is about to be published by MIT Press. It isn't published yet, but the book is already available online. On the official website one can view it in browser but cannot download (as per agreement with the publisher), but it is easy to find a combined PDF e.g. here on github.

• Csaba Szepesvári, Algorithms for Reinforcement Learning, a concise book on RL. A classical, much more detailed but a bit dated textbook is Sutton & Barto, Reinforcement Learning: An Introduction which is also freely available online but only in a cumbersome HTML format.

• Boyd and Vandenberghe, Convex Optimization.

$\hskip{4em}$

Machine Learning

• One the most, if not the most, popular textbooks on machine learning is Hastie, Tibshirani, and Friedman, The Elements of Statistical Learning, which is fully available online (currently 10th printing). It is comparable in scope e.g. to Bishop's Pattern Recognition and ML or Murphy's ML, but those books are not free, while ESL is.

• Hastie & Tibshirani also co-wrote freely available An Introduction to Statistical Learning, With Applications in R which is basically a simpler version of The Elements and focuses on R.

• In 2015, Hastie & Tibshirani co-authored a new textbook Statistical Learning with Sparsity: The Lasso and Generalizations, also available online. This one is quite a bit shorter and focuses specifically on lasso.

• Another freely available all-encompassing machine learning textbook is David Barber's Bayesian Reasoning and Machine Learning. I did not use it myself, but it is widely considered to be an excellent book.

$\hskip{5em}$

Switching now to more specialized topics, there are:

• Rasmussen & Williams Gaussian Processes for Machine Learning, which is the book on Gaussian processes.

• Much awaited Goodfellow, Bengio and Courville Deep Learning textbook that is about to be published by MIT Press. It isn't published yet, but the book is already available online. On the official website one can view it in browser but cannot download (as per agreement with the publisher), but it is easy to find a combined PDF e.g. here on github.

• Csaba Szepesvári, Algorithms for Reinforcement Learning, a concise book on RL. A classical, much more detailed but a bit dated textbook is Sutton & Barto, Reinforcement Learning: An Introduction which is also freely available online but only in a cumbersome HTML format.

• Boyd and Vandenberghe, Convex Optimization.

$\hskip{4em}$

##Machine Learning

One the most, if not the most, popular textbooks on machine learning is Hastie, Tibshirani, and Friedman, The Elements of Statistical Learning, which is fully available online (currently 10th printing). It is comparable in scope e.g. to Bishop's Pattern Recognition and ML or Murphy's ML, but those books are not free, while ESL is.

Hastie & Tibshirani also wrote freely available An Introduction to Statistical Learning, With Applications in R which is a simpler version of The Elements and focuses on R.

In 2015, Hastie & Tibshirani published a new textbook Statistical Learning with Sparsity: The Lasso and Generalizations, also available online.

Another freely available all-encompassing machine learning textbook is David Barber's Bayesian Reasoning and Machine Learning. I did not use it myself, but it is widely considered to be an excellent book.

Switching now to more specialized topics, there are:

• Rasmussen & Williams Gaussian Processes for Machine Learning, which is the book on Gaussian processes.

• Much awaited Goodfellow, Bengio and Courville Deep Learning textbook that is about to be published by MIT Press. It isn't published yet, but the book is already available online. On the official website one can view it in browser but cannot download (as per agreement with the publisher), but it is easy to find a combined PDF e.g. here on github.

• Csaba Szepesvári, Algorithms for Reinforcement Learning, a concise book on RL. A classical, much more detailed but a bit dated textbook is Sutton & Barto, Reinforcement Learning: An Introduction which is also freely available online but only in a cumbersome HTML format.

• Boyd and Vandenberghe, Convex Optimization.

##Machine Learning

• One the most, if not the most, popular textbooks on machine learning is Hastie, Tibshirani, and Friedman, The Elements of Statistical Learning, which is fully available online (currently 10th printing). It is comparable in scope e.g. to Bishop's Pattern Recognition and ML or Murphy's ML, but those books are not free, while ESL is.

• Hastie & Tibshirani also co-wrote freely available An Introduction to Statistical Learning, With Applications in R which is basically a simpler version of The Elements and focuses on R.

• In 2015, Hastie & Tibshirani co-authored a new textbook Statistical Learning with Sparsity: The Lasso and Generalizations, also available online. This one is quite a bit shorter and focuses specifically on lasso.

• Another freely available all-encompassing machine learning textbook is David Barber's Bayesian Reasoning and Machine Learning. I did not use it myself, but it is widely considered to be an excellent book.

$\hskip{5em}$

Switching now to more specialized topics, there are:

• Rasmussen & Williams Gaussian Processes for Machine Learning, which is the book on Gaussian processes.

• Much awaited Goodfellow, Bengio and Courville Deep Learning textbook that is about to be published by MIT Press. It isn't published yet, but the book is already available online. On the official website one can view it in browser but cannot download (as per agreement with the publisher), but it is easy to find a combined PDF e.g. here on github.

• Csaba Szepesvári, Algorithms for Reinforcement Learning, a concise book on RL. A classical, much more detailed but a bit dated textbook is Sutton & Barto, Reinforcement Learning: An Introduction which is also freely available online but only in a cumbersome HTML format.

• Boyd and Vandenberghe, Convex Optimization.

$\hskip{4em}$

This is partially duplicating some existing answers, but I wanted to create a meaningful list on the ML topic.

##Machine Learning

One the most, if not the most, popular textbooks on machine learning is Hastie, Tibshirani, and Friedman, The Elements of Statistical Learning, which is fully available online (currently 10th printing). It is comparable in scope e.g. to Bishop's Pattern Recognition and ML or Murphy's ML, but those books are not free, while ESL is.

Hastie & Tibshirani also wrote freely available An Introduction to Statistical Learning, With Applications in R which is a simpler version of The Elements and focuses on R.

In 2015, Hastie & Tibshirani published a new textbook Statistical Learning with Sparsity: The Lasso and Generalizations, also available online.

Another freely available all-encompassing machine learning textbook is David Barber's Bayesian Reasoning and Machine Learning. I did not use it myself, but it is widely considered to be an excellent book.

Switching now to more specialized topics, there are:

• Rasmussen & Williams Gaussian Processes for Machine Learning, which is the book on Gaussian processes.

• Much awaited Goodfellow, Bengio and Courville Deep Learning textbook that is about to be published by MIT Press. It isn't published yet, but the book is already available online. On the official website one can view it in browser but cannot download (as per agreement with the publisher), but it is easy to find a combined PDF e.g. here on github.

• Csaba Szepesvári, Algorithms for Reinforcement Learning, a concise book on RL. A classical, much more detailed but a bit dated textbook is Sutton & Barto, Reinforcement Learning: An Introduction which is also freely available online but only in a cumbersome HTML format.

• Boyd and Vandenberghe, Convex Optimization.

##Machine Learning

One the most, if not the most, popular textbooks on machine learning is Hastie, Tibshirani, and Friedman, The Elements of Statistical Learning, which is fully available online (currently 10th printing). It is comparable in scope e.g. to Bishop's Pattern Recognition and ML or Murphy's ML, but those books are not free, while ESL is.

Hastie & Tibshirani also wrote freely available An Introduction to Statistical Learning, With Applications in R which is a simpler version of The Elements and focuses on R.

In 2015, Hastie & Tibshirani published a new textbook Statistical Learning with Sparsity: The Lasso and Generalizations, also available online.

Another freely available all-encompassing machine learning textbook is David Barber's Bayesian Reasoning and Machine Learning. I did not use it myself, but it is widely considered to be an excellent book.

Switching now to more specialized topics, there are:

• Rasmussen & Williams Gaussian Processes for Machine Learning, which is the book on Gaussian processes.

• Much awaited Goodfellow, Bengio and Courville Deep Learning textbook that is about to be published by MIT Press. It isn't published yet, but the book is already available online. On the official website one can view it in browser but cannot download (as per agreement with the publisher), but it is easy to find a combined PDF e.g. here on github.

• Csaba Szepesvári, Algorithms for Reinforcement Learning, a concise book on RL. A classical, much more detailed but a bit dated textbook is Sutton & Barto, Reinforcement Learning: An Introduction which is also freely available online but only in a cumbersome HTML format.

• Boyd and Vandenberghe, Convex Optimization.