Hacker News Reader

Interesting! I’ll have to look over it when I have more time.

From a quick glance, it looks like it covers much of the same material as this text [1]. I wonder how they compare.

[1]: https://www.cambridge.org/core/books/understanding-machine-l...

A 2014 book on machine learning sounds quaint and historical.

Depends on what you want from a (text)book. In my mind books should be authoritative, they should include things that have had some thought put into them and are fairly well studied/verified. Modern advances in deep learning/ML are exciting but are very often not this. I would not a read a book which is just some recent hype papers from NeurIPS/ICML stapled together.

It depends on the particular subtopics it covers. Machine Learning: A Probabilistic Perspective is from 2012 and it's still a great resource, although Murphy's newer book will certainly cover more up-to-date material.

Reply on news.ycombinator.com