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.

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

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.

The original Show HN, https://news.ycombinator.com/item?id=44633725

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?

Yes, vanilla neural networks are just lots of perceptrons

I love this visual article as well:

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

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.

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

Lucky you!

<https://visualrambling.space/dithering-part-1/>

<https://visualrambling.space/dithering-part-2/>

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

This visualizations reminds me of the 3blue1brown videos.

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

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).

"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".

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

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.

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

High FPS on Safari M2 MBP.

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

> 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.

Great visualization!

very cool stuff