Hacker News

Understanding Neural Network, Visually

180 points by surprisetalk ago | 23 comments

tpdly |next [-]

Lovely visualization. I like the very concrete depiction of middle layers "recognizing features", that make the whole machine feel more plausible. I'm also a fan of visualizing things, but I think its important to appreciate that some things (like 10,000 dimension vector as the input, or even a 100 dimension vector as an output) can't be concretely visualized, and you have to develop intuitions in more roundabout ways.

I hope make more of these, I'd love to see a transformer presented more clearly.

helloplanets |next |previous [-]

For the visual learners, here's a classic intro to how LLMs work: https://bbycroft.net/llm

esafak |next |previous [-]

This is just scratching the surface -- where neural networks were thirty years ago: https://en.wikipedia.org/wiki/MNIST_database

If you want to understand neural networks, keep going.

brudgers |next |previous [-]

8cvor6j844qw_d6 |next |previous [-]

Oh wow, this looks like a 3d render of a perceptron when I started reading about neural networks. I guess essentially neural networks are built based on that idea? Inputs > weight function to to adjust the final output to desired values?

adammarples |root |parent [-]

Yes, vanilla neural networks are just lots of perceptrons

jazzpush2 |next |previous [-]

I love this visual article as well:

https://mlu-explain.github.io/neural-networks/

jetfire_1711 |next |previous [-]

Spent 10 minutes on the site and I think this is where I'll start my day from next week! I just love visual based learning.

ge96 |next |previous [-]

I like the style of the site it has a "vintage" look

Don't think it's moire effect but yeah looking at the pattern

Bengalilol |root |parent [-]

ge96 |root |parent [-]

Oh god my eyes! As it zooms in (ha)

That's cool, rendering shades in the old days

Man those graphics are so good damn

|next |previous [-]

cwt137 |next |previous [-]

This visualizations reminds me of the 3blue1brown videos.

giancarlostoro |root |parent [-]

I was thinking the same thing. Its at least the same description.

4fterd4rk |next |previous [-]

Great explanation, but the last question is quite simple. You determine the weights via brute force. Simply running a large amount of data where you have the input as well as the correct output (handwriting to text in this case).

ggambetta |root |parent [-]

"Brute force" would be trying random weights and keeping the best performing model. Backpropagation is compute-intensive but I wouldn't call it "brute force".

Ygg2 |root |parent [-]

"Brute force" here is about the amount of data you're ingesting. It's no Alpha Zero, that will learn from scratch.

jazzpush2 |root |parent [-]

What? Either option requires sufficient data. Brute force implies iterating over all combinations until you find the best weights. Back-prop is an optimization technique.

artemonster |next |previous [-]

I get 3fps on my chrome, most likely due to disabled HW acceleration

nerdsniper |root |parent [-]

High FPS on Safari M2 MBP.

anon291 |next |previous [-]

Nice visuals, but misses the mark. Neural networks transform vector spaces, and collect points into bins. This visualization shows the structure of the computation. This is akin to displaying a Matrix vector multiplication in Wx + b notation, except W,x,and b have more exciting displays.

It completely misses the mark on what it means to 'weight' (linearly transform), bias (affine transform) and then non-linearly transform (i.e, 'collect') points into bins

titzer |root |parent [-]

> but misses the mark

It doesn't match the pictures in your head, but it nevertheless does present a mental representation the author (and presumably some readers) find useful.

Instead of nitpicking, perhaps pointing to a better visualization (like maybe this video: https://www.youtube.com/watch?v=ChfEO8l-fas) could help others learn. Otherwise it's just frustrating to read comments like this.

pks016 |next |previous [-]

Great visualization!

javaskrrt |previous [-]

very cool stuff