https://github.com/alexsosn/convnetswift
Swift port of ConvnetJS. [Work in progress]
https://github.com/alexsosn/convnetswift
convnetjs convolutional-neural-networks deep-learning deep-q-network deep-reinforcement-learning machine-learning swift-port
Last synced: about 1 year ago
JSON representation
Swift port of ConvnetJS. [Work in progress]
- Host: GitHub
- URL: https://github.com/alexsosn/convnetswift
- Owner: alexsosn
- License: mit
- Created: 2015-11-09T00:26:19.000Z (over 10 years ago)
- Default Branch: master
- Last Pushed: 2017-03-10T18:21:19.000Z (over 9 years ago)
- Last Synced: 2025-04-11T22:42:41.648Z (about 1 year ago)
- Topics: convnetjs, convolutional-neural-networks, deep-learning, deep-q-network, deep-reinforcement-learning, machine-learning, swift-port
- Language: Swift
- Size: 12.6 MB
- Stars: 43
- Watchers: 7
- Forks: 5
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# ConvNetSwift
Swift port of [ConvnetJS](http://cs.stanford.edu/people/karpathy/convnetjs/) - a library for training Deep Learning models (mainly Neural Networks).
Updated to Swift 3.
Available NN layer types:
- [x] Fully Connected
- [x] Convolutional
- [x] Dropout
- [x] ReLU
- [x] Sigmoid
- [x] Maxout
- [x] Hyperbolic Tangent
- [x] Local Response Normalization
- [x] Max Pooling
- [x] Output: Softmax, Regression, SVM
Optimization methods ('trainers'/'solvers'):
- [x] Stochastic Gradient Descent
- [x] Adam
- [x] Adaptive Gradient
- [x] WindowGrad
- [x] AdaDelta
- [x] Nesterov’s Accelerated Gradient
Reinforcement learning:
- [x] Q-learning
Acceleration:
- [ ] Accelerate framework
- [ ] Metal
This is not a production-ready library. It is a personal research project and work in progress.