ConvNetJS

A ConvNetJS is a neural net training system that is based on JavaScript Programming Language.

• Context:
  • It can train Deep Learning Neural Networks.
• Example(s):
  • ConvnetJS demo: toy 2d classification with 2-layer neural network,
  • ConvNetJS MNIST demo,
  • ConvNetJS CIFAR-10 demo,
  • ConvnetJS demo: toy 1d regression,
  • ConvNetJS Denoising Autoencoder demo,
  • ConvNetJS Deep Q Learning Demo,
  • ConvnetJS demo: Image "Painting",
  • ConvNetJS Trainer demo on MNIST
• Counter-Example(s):
  • PyTorch;
  • TensorFlow;
  • DeepLearning4J;
  • MXNet.
• See: Convolutional Neural Network Training System, Reinforment Learning, Deep Learning, Artificial Neural Network, Machine Learning Regression, Machine Learning Classification.

---

---

References

2018a

• (Karpathy, 2018a) ⇒ Andrej Karpathy (2018). https://cs.stanford.edu/people/karpathy/convnetjs/index.html Retrieved: 2018-08-18.
  • QUOTE: 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.

(...)

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.

2018b

• (Karpathy, 2018b) ⇒ Girhub Release: https://github.com/karpathy/convnetjs Retrieved: 2018-08-18.
  • QUOTE: ConvNetJS is a Javascript implementation of Neural networks, together with nice browser-based demos. It currently supports:
    • 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.

For much more information, see the main page at convnetjs.com

---