from Hacker News

Alice's Adventures in a Differentiable Wonderland

by henning on 6/30/25, 6:02 PM with 26 comments

  • by bwfan123 on 7/3/25, 5:54 PM

    this 3 page classic [1] captures most of the core ideas and explains it in a manner anyone with basic calculus background can understand - "Learning representations by back-propagating errors"

    [1] https://gwern.net/doc/ai/nn/1986-rumelhart-2.pdf

  • by _giorgio_ on 7/3/25, 2:27 PM

  • by superjose on 7/3/25, 2:11 PM

    Wow, kudos to the Author. Very easy to digest, beautifully crafted, and took the time to explain the concepts when most places take them for granted.

  • by 0cf8612b2e1e on 7/3/25, 5:07 PM

      The corresponding row vector is denoted by x^T when we need to distinguish them. We can also ignore the transpose for readability, if the shape is clear from context.
    I am tilting at windmills, but I am continually annoyed at the sloppiness of mathematicians in writing. Fine, you don’t like verbosity, but for didactic purposes, please do not assume the reader is equipped to know that variable x actually implies variable y.

    All that being said, the writing style from the first chapter is very encouraging at how approachable this will be.

  • by magnio on 7/3/25, 2:12 PM

    This looks like a good practical companion for a more theoretical text, such as Deep Learning by Bishop.

  • by odyssey7 on 7/3/25, 3:30 PM

    It would be nice if arXiv included a small-layout pdf or native epub option for e-readers. Now that they serve the Tex files and are experimenting with HTML, it feels like a natural step.

  • by fossa1 on 7/3/25, 1:15 PM

    Glad to see JAX featured alongside PyTorch. JAX still feels like the best-kept secret in deep learning

  • by canyp on 7/3/25, 11:13 PM

    Beautifully formatted and has the right combination of code and theory for noobs like me. Strong vibes for Simone right now, hero of the people.

  • by dunefox on 7/3/25, 8:55 PM

    And I just bought the physical book...

  • by kittikitti on 7/3/25, 2:24 PM

    Although I love this, it's not peer reviewed and I don't trust arxiv.

  • by ProofHouse on 7/3/25, 1:56 PM

    Damn beeeeefffffyyyyy. Need the month to eat ten pages a day, Tnx looks awesome. Could append diffusion too ultimately