I’m trying to learning machine learning from a more mathematical/theory side of machine learning just so its easier for me to understand AI/ML papers that are coming out just to keep up with them. I would say that I have a basic understanding of AI/ML but more so on the applied side like in Keras, TF, PyTorch somewhat but I feel like I am lacking on my understanding on the mathematical side of AI/ML. So any books and course recs for that?

  • gmatkins@sh.itjust.works
    link
    fedilink
    English
    arrow-up
    7
    ·
    1 year ago

    Mathematics for Machine Learning by Marc Deisenroth and Deep Learning by Ian Goodfellow. Two great books for theory but practice always helps too.

    • joba2ca@feddit.de
      link
      fedilink
      English
      arrow-up
      4
      ·
      1 year ago

      I also recommend Deep Learning by Goodfellow. Long chapter about the mathematical foundations. I found it very insightful as side lecture during my studies. Also, the online version is free.

      • __forward__@lemm.ee
        link
        fedilink
        English
        arrow-up
        3
        ·
        1 year ago

        Yes! This is an amazing book! It has all the neural models in great detail, considering the detail it goes into it’s also very readable.

  • konodas@feddit.de
    link
    fedilink
    English
    arrow-up
    4
    ·
    edit-2
    1 year ago

    Pattern Recognition and Machine Learning from Bishop is really good, imho. Its relatively math-heavy, so depending on your skill, reading Mathmatics for ML or Linear algebra and optimization for ML by c. aggarwal might be a good idea.

      • konodas@feddit.de
        link
        fedilink
        English
        arrow-up
        1
        ·
        1 year ago

        I enjoyed it. Linear algebra and optimization are treated much more in depth compared to MML. IIRC he then goes to linear regression and derives most other models from there, which is an interesting perspective.