[HN Gopher] Alice's Adventures in a Differentiable Wonderland
___________________________________________________________________
Alice's Adventures in a Differentiable Wonderland
Author : henning
Score : 119 points
Date : 2025-06-30 18:02 UTC (3 days ago)
(HTM) web link (arxiv.org)
(TXT) w3m dump (arxiv.org)
| fossa1 wrote:
| Glad to see JAX featured alongside PyTorch. JAX still feels like
| the best-kept secret in deep learning
| ProofHouse wrote:
| Damn beeeeefffffyyyyy. Need the month to eat ten pages a day, Tnx
| looks awesome. Could append diffusion too ultimately
| superjose wrote:
| 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.
| magnio wrote:
| This looks like a good practical companion for a more theoretical
| text, such as Deep Learning by Bishop.
| kittikitti wrote:
| Although I love this, it's not peer reviewed and I don't trust
| arxiv.
| SiempreViernes wrote:
| Actually, it _is_ peer reviewed following the standard practice
| for books: some other people read it and provided feedback as
| evidenced by the Acknowledgments section.
| esafak wrote:
| People are submitting corrections:
| https://www.sscardapane.it/assets/alice/errata_list.pdf
| odyssey7 wrote:
| It's more a book than academic research.
|
| The funny thing about books is that authors in free societies
| are allowed to self-publish whatever they want. The norms are
| different and, frankly, more democratic and with less
| gatekeeping.
| ethan_smith wrote:
| arXiv is a preprint server trusted by the scientific community
| for decades - papers there often undergo peer review later, and
| many top ML researchers publish their work there first for
| faster dissemination.
| _giorgio_ wrote:
| Website of the author with more material and lab sessions
|
| https://www.sscardapane.it/alice-book/
|
| https://sscardapane.notion.site/Guided-lab-sessions-18c25bd1...
| odyssey7 wrote:
| 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.
| 0cf8612b2e1e wrote:
| 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.
| JadeNB wrote:
| > 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.
|
| I am a practicing mathematician who felt the same way you did
| when I started, and who still writes their papers in a way that
| many of my colleagues feel is gallingly pedantic. With that as
| my credentials, I hope I may say that it can be much worse as a
| reader to read something where every detail is spelled out,
| because a bit of syntactic sugar begins to seem as important as
| the heart of an argument. Where the dividing line is between
| precision and obfuscation depends on the reader, and so
| inevitably will leave some readers on the wrong side, but a
| trade-off does have to be made somewhere.
| runeblaze wrote:
| It is weird to be honest. I first learned Coq and then started
| taking upper level maths classes. My group theory proofs were
| panned by my TAs as overly verbose, very precise, and I was
| specializing on H_1 and H_2s everywhere and having IHns flying
| around like crazy because I _could not fathom_ how one proves
| things without formally connecting things up.
|
| Then my profs told me I was not "wrong", but proofs or
| expositions are to most mathematicians not programs (ha! How
| did I not know. You teach me natural deduction and expect me
| _not_ to program?), more like convincing arguments /prose. At
| some point one abstracts.
| bwfan123 wrote:
| 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
| dunefox wrote:
| And I just bought the physical book...
___________________________________________________________________
(page generated 2025-07-03 23:01 UTC)