Cool Machine Learning Books
matpalm.com
matpalm.com
That said, most of the descriptions on this page are not detailed enough to tell me anything useful about them. There is little specific about, say, author perspectives, level of formalism vs appeals to intuition, interesting proofs or explanations of particular theorems/topics, helpful or not indexes, etc.
Saying "X book is great" or "I liked book X" and not giving a reason does nothing for me. As written, these reviews detract from the list because they draw the eye to no benefit. As a rule of thumb, the words "good", "great", and "epic" should be avoided at all costs in this kind of writing
I apologize for being harsh -- I'm giving this feedback because I didn't notice any affiliate links which suggests to me that you do want for this to be a useful resource (not that it wouldn't be true if it had affiliate links, just would suggest other motivations took greater priority)
Thanks for spending the time on it regardless
Lectures: https://ocw.mit.edu/courses/mathematics/18-06-linear-algebra...
I saw enough books on the list that I recognized and benefited from to convince me that the author has some idea of what they're talking about. That's enough to convince me that some of the other books on the list might be worth checking out.
Once you have a book title in mind, there are lots of resources you can use to find out whether it's worth reading -- Amazon comments, book reviews, the publisher's website, the table of contents, published excerpts, etc etc etc.
The most important part of a book search on the internet today is title discovery: picking one book to look at out of the gazillion books available. The author seems to have taken a pretty good stab at that.
I've always wanted to be able to "annotate" a textbook I was reading ::in-place::, and write my own "local" version of the text.
I was in college during the early late 90s, early 2000s, that was a winter time for ML.Besides the perennial AI, the popular term was "soft computing" to include not only neural networks, but also stuff like fuzzy logic, evolutionary algorithms and simulated annealing. I found it all the approaches so fascinating. For better or for worse the DL explosion totally eclipsed the rest of approaches. Does anybody know of recent relevant work on those fields?