A Neural Network That Writes Hangul by Hand
A write-up on training a recurrent neural network to generate Korean handwriting strokes, from collecting 4,500 lines with a smartpen to adapting Alex Graves' method.
No account needed · sign in to keep your taste everywhere
More like this
Pages that share this page's themes. Or browse all of Tech.
Kanji RNN
A sketch-rnn model trained on kanji that draws plausible-looking but invented characters stroke by stroke in your browse…
Can You Reverse Engineer Our Neural Network?
Jane Street presents a machine learning puzzle: given a trained network and no documentation, work out what it actually…
Self Driving Cars Are Fun!
A student's write-up of building a self-driving car autopilot in Keras, walking through training a neural network to ste…
GAN Playground
Train generative adversarial networks entirely in your browser and watch them learn to imitate 2D distributions or image…
Neural Network Evolution Playground
Watch a genetic algorithm evolve odd little neural networks that learn to classify 2D datasets, with live visualizations…
Read Korean Letters
A free crash course that teaches you to read Hangul in about two hours, with a quiz to test yourself and songs with subt…
Stumble onto more like this
One click takes you to a page you didn't know you were looking for. Rate it and the next one lands closer to your taste.
Add to Browser — it's freeWorks in Chrome, Edge and Brave. No account needed.