ConvNetJS

Browser Demos

Classify MNIST digits with a Convolutional Neural Network

Classify CIFAR-10 with Convolutional Neural Network

Interactively classify toy 2-D data with a Neural Network

Interactively regress toy 1-D data

Train an MNIST digits Autoencoder

Reinforcement Learning with Deep Q Learning

Neural Network "paints" an image

Comparing SGD/Adagrad/Adadelta

Description

The library allows you to formulate and solve Neural Networks in Javascript, and was originally written by @karpathy (I am a PhD student at Stanford). However, the library has since been extended by contributions from the community and more are warmly welcome. Current support includes:

• Common Neural Network modules (fully connected layers, non-linearities)
• Classification (SVM/Softmax) and Regression (L2) cost functions
• Ability to specify and train Convolutional Networks that process images
• An experimental Reinforcement Learning module, based on Deep Q Learning.

Head over to Getting Started for a tutorial that lets you get up and running quickly, and discuss Documentation for all specifics.

Code

The code is available on Github under MIT license and I warmly welcome pull requests for new features / layers / demos and miscellaneous improvements. The library is also available on npm for use in Nodejs, under name convnetjs.

Discussion Group