11 comments

[ 3.3 ms ] story [ 37.8 ms ] thread
Neural networks are a beautiful concept. They are also beautiful to watch. I created an interactive neural network visualizer and tutorial. It’s a fun way to develop some intuition about neural nets. It was created using vis.js, and a lot of love. Hope you enjoy!
that is so cool and a really clear tutorial. does it use three?
Glad you enjoyed it! It uses a library called vis.js.
That's fun, but the whole point of neural networks is to train them against data, not tweak the weights by hand. Hand-tuning a neural network is not done much - it's like setting raw filter parameters by hand.
True, but it's useful to get an intuitive understanding quickly. This doesn't go into the various loss functions or neuron types or matrices, just play-with-it level intuition. I bookmarked it under "Research/MachineLearning/Intro"
Well said. That's exactly the point: to get "play-with-it level intuition". Even though its not rigorous, I still find it helps.

I am planning on building a simulation of the back-prop algorithm though!

really cool! is the source on github?
The guy doesn't have the habit to open-source.
Thanks!

Yes. I will be posting the source to github very soon.

Wow, this is an amazing intro to neural networks, thanks!