News for hackers. Stuff that matters.
Re:Probabilistic Machine Learning: Advanced Topics by ayhanfuat on Tuesday August 15, 2023 @04:01PM (#37138626)
Both the intro and this one are great reference books but I don't find them suitable to study as the main textbook. They cover a large number of topics so the depth of each topic is pretty limited. Keep in mind if you are considering to study these.
Re:Probabilistic Machine Learning: Advanced Topics by pajep on Tuesday August 15, 2023 @04:11PM (#37138760)
what are some good book for people that want to start master in ML?
Re:Probabilistic Machine Learning: Advanced Topics by runningmike on Tuesday August 15, 2023 @04:34PM (#37139000)
an opinionated list of great machine learning learning resources: https://nocomplexity.com/documents/fossml/mlcourses.html
Re:Probabilistic Machine Learning: Advanced Topics by ayhanfuat on Tuesday August 15, 2023 @04:21PM (#37138865)
With a similar probability focus, Pattern Recognition and Machine Learning by Christopher Bishop is pretty good. If you are looking into deep learning specifically, I think François Chollet's Deep Learning with Python is one of the most accessible books.
Re:Probabilistic Machine Learning: Advanced Topics by gexaha on Tuesday August 15, 2023 @05:39PM (#37139607)
I think "Understanding Deep Learning" is very nice - https://udlbook.github.io/udlbook/ (an covers almost all topics, it has maybe just a couple of omissions, such as Multimodal Learning, NERFs and Time Series Prediction)
Re:Probabilistic Machine Learning: Advanced Topics by mhh__ on Tuesday August 15, 2023 @06:05PM (#37139864)
Ironically I found it to be too deep. I want a quick feel for the mathematical structure and ergonomics of a field before really diving into 400 pages on logistic regressions.
Re:Probabilistic Machine Learning: Advanced Topics by nextos on Tuesday August 15, 2023 @07:15PM (#37140556)
I think it gets to a sufficient depth if you also consider the Supplementary Material and Jupyter Notebooks hosted on GitHub.

But for those with no ML background, the place to start is: https://mml-book.github.io/

Re:Probabilistic Machine Learning: Advanced Topics by quanto on Tuesday August 15, 2023 @07:32PM (#37140755)
I did not find the intro book a good book at all.

The text was full of non-trivial errors that genuinely hindered students' understanding. Moreover, the presentation was not particularly enlightening -- lengthy mathematical discussions therein were not neither rigorous enough for a proper mathematical introduction; nor distilled enough for an application practitioners. I understand that Murphy explicitly tried to strike a balance -- I wonder if this balance ended up being in the awkward no man's land.

I found the book better as a secondary source due to its breadth of topics. The second book seems to continue this trend of covering even more topics.

Re:Probabilistic Machine Learning: Advanced Topics by npalli on Tuesday August 15, 2023 @09:05PM (#37141497)
>The text was full of non-trivial errors that genuinely hindered students' understanding

Kudos to the author for putting out a free version and for the work but the number of errors seems crazy high (I checked a couple and doesn't seem like they were fixed in the 2023-06-21 draft pdf he has put on his website), I have the 2022 book so definitely have to look into the error list.

https://github.com/probml/pml-book/issues?page=12&q=is%3Aiss...