Yet another Hacker News

The Little Book of Generative AI Foundations: An Intuitive Mathematical Primer

173 points ibobev 2 hours ago 25 comments

prideout 2 hours ago | parent

My favorite little book is François Fleuret's: The Little Book of Deep Learning https://fleuret.org/francois/lbdl.html

arcanemachiner 2 hours ago | parent

I love how that site offers a phone-formatted PDF as an option. How thoughtful!

dominotw 50 minutes ago | parent

i got duo to increase my reading.

qifzer 30 minutes ago | parent

You may enjoy the reflow feature on Koreader. It fits a pdfs content into a screenwidth single column layout. That text is also zoomable.

CamperBob2 2 hours ago | parent

It's a nice treatment of the subject, but I wish he would post a conventionally-formatted .PDF that puts every page on a full sheet of standard printer paper.

bscphil 1 hour ago | parent

I immediately wanted the same thing, so I made it. The book is licensed Creative Commons BY-NC-SA 4.0 International License, so here you go.

https://cdn.filepost.dev/file/filepost/uploads/15/1578f21219...

CamperBob2 1 hour ago | parent

Thanks!

joe_the_user 30 minutes ago | parent

I'd note that the Fleuret books gives the foundation for basic deep learning whereas the OP seems to give the necessary foundations for Transformers and related machinery. These later addition what is now "AI" are in total at least as complicated as the original deep learning concepts. Not that just learning basic neural networks but the two book don't appear to cover the same ground.

wh306 11 minutes ago | parent

Only had a quick skim, but looks like the content of this book has very little to do with transformers. Might be more relevant for diffusion models (image/video generation) though.

amplifydev 2 hours ago | parent

Interesting!

Is there any one who have recommended books on the attention architecture specifically? I have been interested in that for a long time but never gotten around to actually studying it.

achandra03 2 hours ago | parent

Not a book, but 3blue1brown's video on attention is pretty great: https://www.youtube.com/watch?v=eMlx5fFNoYc

horseloverthin 1 hour ago | parent

formal algorithms for transformers provides perhaps the most succinct introduction to attention I can imagine https://arxiv.org/pdf/2207.09238

minimaxa 1 hour ago | parent

Appreciated, I drop all of these into a RAG folder for when I need them later on in projects.

8Gb of whitepapers/books...

plicense 1 hour ago | parent

Can you share what you have so far in that folder?

gerdesj 53 minutes ago | parent

They spell it out quite clearly: "8Gb of whitepapers/books..."

cheesewhistle 47 minutes ago | parent

I'm v curious how you're incorporating this into your workflow. Is it that when you want to implement something you can call out to these books as rigorous reference material for your agents? I'd never thought of doing such a thing and am curious how you're doing it and how it's worked.

nblgbg 1 hour ago | parent

Are there any deep learning books with some problems to solve ?

p1esk 1 hour ago | parent

Wow, this book is surprisingly readable! I like how he starts from basics of linear algebra.

3abiton 43 minutes ago | parent

Someone should add it to the hacker news curated paper list! Along side the video and book list.

StilesCrisis 22 minutes ago | parent

The very first formula in the text, explicitly described as "as simple as possible," names its variable ê1 with no explanation given. I think this paper needs another pass.

nhatcher 15 minutes ago | parent

That's absolutely standard notation for a unit basis vector. I haven't read the prerequisites carefully, so if it addressed to the general public maybe?

It is perhaps addressed to a different crowd?

mkl 9 minutes ago | parent

It's just giving a vector a name. It also names ê₂. These particular names are very standard and familiar to most people who've met vectors before.

You can look at those vectors and see that the position of the 1 is the subscript, without explanation. The ^ could do with an explanation that it means unit vector, but if you've met vectors before you likely know that (maybe that's elsewhere in the book, but a quick search didn't find it).

apricot 2 minutes ago | parent

What do you mean "no explanation given"? It says: "In 2 dimensions, the standard (or identity) basis vectors are ê1 = [ 1 0 ] and ê2 = [0 1]." Seems pretty clear to me he's defining ê1 and ê2, or rather telling us that he's using this very common way of naming the basis vectors.

Daklone 17 minutes ago | parent

We are recommending books for HackerBooks.org I see. Good, this is why I have come here also.

Let me tell you about one of the greatest book series of our generation: Dungeon Crawler Carl, By Matt Dinniman

https://mattdinniman.com/books/

From the Dust jacket: The apocalypse will be televised!

You know what’s worse than breaking up with your girlfriend? Being stuck with her prize-winning show cat. And you know what’s worse than that? An alien invasion, the destruction of all man-made structures on Earth, and the systematic exploitation of all the survivors for a sadistic intergalactic game show. That’s what. READ MORE

Join Coast Guard vet Carl and his ex-girlfriend’s cat, Princess Donut, as they try to survive the end of the world—or just get to the next level—in a video game–like, trap-filled fantasy dungeon. A dungeon that’s actually the set of a reality television show with countless viewers across the galaxy. Exploding goblins. Magical potions. Deadly, drug-dealing llamas. This ain’t your ordinary game show.

Welcome, Crawler. Welcome to the Dungeon. Survival is optional. Keeping the viewers entertained is not.

Published sept 21, 2020 RePublished Aug 27, 2024

northes 12 minutes ago | parent

The street marketing around this book is frankly baffling, do you suppose this is relevant?