I vibecoded this neural network visualization for my students and open sourced it.
@DFinsterwalder2,5 B takipçi
488.596 görüntüleme
65 Yorum
Yorumlar X (Twitter) üzerindeki orijinal gönderiden alınmıştır

@DFinsterwalder
Before I say a couple more words here is a link to play with it: Everything runs in a browser and the weights are stored in a json. Might take a bit to load on slower connection. Also its intended for desktop/larger screens and menu overlaps on mobile.
72 beğeni

@DFinsterwalder
Here is the github repo with all the code for training and visualization all under Apache 2.0 licence.
121 beğeni

@DFinsterwalder
So first of all sorry for all the text being in German. I wanted to translate it to English before sharing it, but didn't have the time. Also in the current form the educational information is limited since it was used in class with me explaining it.
20 beğeni

@DFinsterwalder
When I have a bit more time I go over it and will translate it and make it more standalone educational. Also I am currently talking with an exhibition to use it and I might add an option to connect a tablet to it via WebRTC to paint the numbers there.
11 beğeni

@DFinsterwalder
This was 100% vibecoded using Codex and similar to other things this worked flawless, because of how amazing @threejs is. The @pytorch code for an MLP is obviously trival and also was no challenge. See this thread for something similar that I vibecoded.
47 beğeni

@DFinsterwalder
The visualisation is inspired by @3blue1brown cover image for this video. If you don't know his content and want to learn more about neural networks I recommend watching his videos.
62 beğeni

@DFinsterwalder
If you enjoy posts consider retweeting it. And if you like tweets about vibecoding, neural networks, AI, 3D, philsophy and shitposting consider following me.
21 beğeni

@DFinsterwalder
Since a couple of people are posting fail cases. Yes this is known and basically intended. I showed the fail cases in class. It’s a simple neural network architecture and small. We known better methods since the 90s for this (conv nets) and training should do data augmentation.
9 beğeni

@DFinsterwalder
Here is a video of @ylecun showing convolution neural networks in 1989 that work better than this MLP here (but are a bit more complicated to explain and visualize). Fun fact: the MNIST dataset used is also from Yann LeCun.
12 beğeni

@_junaidkhalid1
Honestly.. this is a brilliant way to bridge the gap between theory and application for students. Visualizing something like an MLP in real-time makes the learning process so much more intuitive. Am thinking if tools like this could also help researchers experiment with architectures more interactively.. or is it primarily built with teaching in mind?
14 beğeni

@DFinsterwalder
@threejs @PyTorch I think its more useful for teaching core principles. The architecture is super small. Its just 110.000 parameters. LLMs have billions of parameter and more complicated connections.
3 beğeni

@SkepticistBoy
@threejs @PyTorch Seems almost like a copy of
7 beğeni

@DFinsterwalder
@threejs @PyTorch Yeah I saw that one when I researched whats already out there to show my students, but I didn't really like it flattened out neurons and that it doesn't show (some) weights while updating. It's actually much more inspired by (or copying) this from @3blue1brown
5 beğeni

@SkepticistBoy
@threejs @PyTorch @3blue1brown I appreciate your efforts to demonstrate your students in the best possible way.
1 beğeni

@CualesDeMileto
@threejs @PyTorch
7 beğeni

@DFinsterwalder
@threejs @PyTorch Awesome. Showing the training is cool!
1 beğeni

@CualesDeMileto
@threejs @PyTorch Also I made some experiment simulating combinational logic system and a secuential RISC-V architecture (flip-flops, etc...) and fusing it with the NN system too 😂
3 beğeni

@CualesDeMileto
@threejs @PyTorch
2 beğeni

@DFinsterwalder
@threejs @PyTorch Awesome! The most complex thing I designed with flip flops was a number counter with a single digit seven-segment LCD display. NNs on RISC-V is great!
1 beğeni

@hysmio
@threejs @PyTorch Did the same thing not too long ago, super interesting to dig through
3 beğeni





























