Little Learner
by Daniel P. Friedman, Anurag Mendhekar · first published 2023
67% recommend33% neutral
Why HN recommends it
Taught through Scheme with a gentle, question-driven style that builds deep learning concepts from first principles; suits programmers who want to understand neural networks without heavy math or frameworks.
Summarised by Claude from recommending comments
Affiliate links. As an Amazon Associate I earn from qualifying purchases.
Mentions per year
What Hacker News says
Related books
Little Prover
Daniel P. Friedman, Carl Eastlund, Duane Bibby
Recommended by 9 · mentioned by 189 recommend · 18 mention9 recommend · 189 recommend
2007–2026The seasoned schemer
Daniel P. Friedman
Recommended by 33 · mentioned by 4733 recommend · 47 mention33 recommend · 4733 recommend
2008–2025The little MLer
Matthias Felleisen
Recommended by 6 · mentioned by 116 recommend · 11 mention6 recommend · 116 recommend
2018–2026The Little Typer
Daniel P. Friedman, David Thrane Christiansen
Recommended by 16 · mentioned by 3316 recommend · 33 mention16 recommend · 3316 recommend
2007–2026The reasoned schemer
Daniel P. Friedman
Recommended by 45 · mentioned by 7945 recommend · 79 mention45 recommend · 7945 recommend
2007–2026The Little Schemer
Daniel P. Friedman, Matthias Felleisen
Recommended by 288 · mentioned by 438288 recommend · 438 mention288 recommend · 438288 recommend
2007–2026On LISP
Paul Graham
Recommended by 192 · mentioned by 355192 recommend · 355 mention192 recommend · 355192 recommend
2007–2026How to Design Programs
Matthias Felleisen
Recommended by 277 · mentioned by 440277 recommend · 440 mention277 recommend · 440277 recommend
I see Lisp I upvote ;) For the curious, Daniel Friedman and Anurag Mendhekar wrote a book called “The Little Learner”: https://www.thelittlelearner.com/
on “New Racket Deep Learning Library” ↗I've been using Racket to work through The Little Learner[1] and it's been a good experience. You need minimal Racket to work through the book (lambda, let, define, map; I think that's about it). But I branched out to learn more about the language and the standard…
on “Racket v9.1” ↗…However, this is only important once you have a solid interface for working with matrices. If you want to get a feel for the difference I would suggest reading through the surprisingly excellent The Little Learner. I think you'll find that while it really demonstrates the power of Scheme (Racket in this case) in areas where it excels, you wouldn't want to use the framework in that book for anything other than toy…
on “Interactive Common Lisp Development” ↗I second this. Given your background (lisper) maybe do the Little Learner book once it is out + Karpathy's video series. Follow it up by building a slightly complicated application in your favourite domain (text, images, videos, time series). Also word of advise from my experience…
on “The Little Learner: A Straight Line to Deep Learning” ↗I have recently read "The Little Learner" and was quite amazed how much I knew already just because I know APL/J. With the right libraries, these vector languages would be perfect for neural network / deep learning tasks.
on “From Deep Learning Foundations to Stable Diffusion (Part 2)” ↗The Little Learner[0]: Learn the basics using scheme. This is fundamental; no frameworks, just Scheme and functions. From here you can go anywhere. Then watch Neural Networks: Zero to Hero[1] to learn how autograd works,…
on “Ask HN: What's your best resource for keeping up-to-date on AI developments?” ↗I am working my way through "The Seasoned Schemer". Maybe I will go for "The Reasoned Schemer" next. Or "The Little Learner". Great series of books.
on “Ask HN: What Are You Learning?” ↗# Books I've liked that are approachable: - [The Elements of Statistical Learning](https://link.springer.com/book/10.1007/978-0-387-84858-7) - [The Little Learner: A Straight Line to Deep Learning](https://mitpress.mit.edu/9780262546379/the-little-learner/) - [The StatQuest Illustrated Guide To Machine Learning](https://www.amazon.com/dp/B0BLM4TLPY) # Online…
on “Ask HN: How to Transition from Software Engineer to AI/ML Engineer” ↗…solid understanding of programming, familiarity with scheme and the books come from a time when every serious engineer had basic calc knowledge. These are classics (and I was really impressed with "The Little Learner") but are very serious and challenging texts, that outside the first book, are aimed at advanced readers (and for those readers are true delights).
on “The Little Learner: A Straight Line to Deep Learning” ↗The Little Learner is a great book. I tried rewriting all the code in Python/JAX while following the Scheme code style as closely as possible, and it worked out great. The appendix on autodiff is a bit rushed, in my opinion.…
on “Racket v9.1” ↗…allows for logical/relational programming (look up Prolog and Datalog as languages in the same vein). The Little Typer is the linked book covering type systems and, specifically, dependent typing. The Little Learner covers machine learning. The Little Prover uses the same format and has you develop proofs. Little, Seasoned, and Reasoned are, IMO, the better books in the series to start with. I found the later ones…
on “The Little Typer (2018)” ↗…Numbers in, numbers out, and if the wrong numbers come out then God help you. I digress. Is there a distinction between encoding, embedding, and projection I should be aware of? I recently read in "The Little Learner" book that finding the right parameters is learning. That's the point. Everything we do in deep learning is focused on choosing the right sequence of numbers and we call those numbers parameters. Every…
on “Transformers from Scratch” ↗…nowhere (also had no problem to pay twice for the book). The Kindle version of it does not even have fixed table cell width for the layout of the conversation. German book website buecher.de has "The Little Learner" to preorder as ePUB with Adobe DRM. I don't know, if you can buy digital books on this site outside of Germany. Also notice, that copy-protected digital books on this website are highly unusual; most…
on “The Little Learner: A Straight Line to Deep Learning” ↗I thought Little Learner assumed you already knew Lisp/scheme. You'd probably want to go through at LEAST Little Schemer from same author first to get the basics.
on “Common Lisp Implementations in 2023” ↗I've been reading The Little Learner, which builds machine learning knowledge on top of Scheme / Racket. After that book, you could watch this series, which will immediately begin explaining how the automatic differentiation works.
on “Neural Networks: Zero to Hero” ↗