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.
8cvor6j844qw_d6 26 minutes ago [-]
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?
I get 3fps on my chrome, most likely due to disabled HW acceleration
nerdsniper 35 minutes ago [-]
High FPS on Safari M2 MBP.
cwt137 2 hours ago [-]
This visualizations reminds me of the 3blue1brown videos.
giancarlostoro 2 hours ago [-]
I was thinking the same thing. Its at least the same description.
ge96 2 hours ago [-]
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
4fterd4rk 4 hours ago [-]
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 3 hours ago [-]
"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 3 hours ago [-]
"Brute force" here is about the amount of data you're ingesting. It's no Alpha Zero, that will learn from scratch.
jazzpush2 13 minutes ago [-]
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.
pks016 1 hours ago [-]
Great visualization!
anon291 1 hours ago [-]
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 34 minutes ago [-]
> 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.
javaskrrt 2 hours ago [-]
very cool stuff
Rendered at 20:02:21 GMT+0000 (Coordinated Universal Time) with Vercel.
I hope make more of these, I'd love to see a transformer presented more clearly.
https://mlu-explain.github.io/neural-networks/
If you want to understand neural networks, keep going.
Don't think it's moire effect but yeah looking at the pattern
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
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.