I'm looking for a modern machine learning book with graduate-level treatment of more recent topics such as diffusion and generative models, transformers etc.

I have a hard copy of Deep Learning by Goodfellow and Bengio; while I liked the book and read it extensively when it was published, it is a bit dated now.

I'm considering Probabilistic Machine Learning: Advanced Topics by Kevin Patrick Murphy. But maybe there are better alternatives.

I need this for my comprehensive Ph.D. examination. Any suggestions are very appreciated.

P.S. I'm also aware of this stack post, but the list of references there is quite dated or introductory.


1 Answer 1


Berkeley CS294-158 is a graduate-level course on deep unsupervised learning. They cover a lot of architectures used in modern generative modeling. They have recorded lectures and slides online.

Stanford CS236 is a course on deep generative modeling. They don't have a textbook, but they have course notes and slides online.

  • 1
    $\begingroup$ What part of "I'm looking for a modern machine learning book" is not understandable? $\endgroup$
    – nbro
    Commented Jul 24, 2023 at 10:23
  • 1
    $\begingroup$ A good resource is a good resource. I doubt the medium that resource comes in is a deal-breaker for someone studying for an exam. Especially because they're looking for resources on relatively recent topics (e.g., diffusion in the context of deep generative modeling only came out in 2020). Good quality textbooks aren't published in three years -- course notes are going to be close to the best resource you can get. $\endgroup$ Commented Jul 24, 2023 at 11:09
  • $\begingroup$ I totally understand what you're getting at, but I thought it'd be more helpful to at least point them in the direction of helpful resources instead of just leaving the question answered. $\endgroup$ Commented Jul 24, 2023 at 11:11
  • 1
    $\begingroup$ Let's put it in this way. Let's say I'm looking for the Lord of the Rings films and instead you give me the book. Thanks a lot, but that's not what I ask - I don't like reading. Anyway, the OP will decide if your answer is fine. $\endgroup$
    – nbro
    Commented Jul 24, 2023 at 16:15
  • $\begingroup$ @AlexanderWan Thanks for the links, I guess it is a good material for self-study, but this is not what I'm looking for. Anyways, upvoted. $\endgroup$
    – user74376
    Commented Jul 25, 2023 at 5:22

You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .