We had a discussion on the pymc_devs channel about what books to recommend to people wants to learn Machine Learning from a Bayesian perspective. I think it is worth to share:
To me, the classic Christopher Bishop is a must read:
Pattern recognition has its origins in engineering, whereas machine learning grew out of computer science. However, these activities can be viewed as two facets of the same field, and together they have undergone substantial development over the past...
@colcarroll and @fonnesbeck recommended Murphy along with Hastie & Tibshirani:
http://www.cs.ubc.ca/~murphyk/MLbook/
This book describes the important ideas in a variety of fields such as medicine, biology, finance, and marketing in a common conceptual framework. While the approach is statistical, the emphasis is on concepts rather than mathematics. Many...
http://statweb.stanford.edu/~tibs/ElemStatLearn/
9 Likes
Bayesian Data Analysis, by Andrew Gelman, John Carlin, Hal Stern, David Dunson, Aki Vehtari, and Donald Rubin is another good read
http://www.stat.columbia.edu/~gelman/book/
2 Likes
The âpuppy bookâ by John Kruschke is a good read, even for un-initiated. "Doing Bayesian Data Analysis"
https://sites.google.com/site/doingbayesiandataanalysis/
Murhpy is my go-to reference for most of ML
1 Like
I read the first few chapters of âStatistical Rethinkingâ by McElreath and really like his style of writing.
In general I find that reading several authors on the same subject is very helpful to develop understanding.
https://www.crcpress.com/Statistical-Rethinking-A-Bayesian-Course-with-Examples-in-R-and-Stan/McElreath/p/book/9781482253443
1 Like
Yes, this book is really great. @aloctavodia has ported much of it to PyMC3.
1 Like