Machine Learning in Haskell with a focus on neural networks.
NOTE: This was mostly an experiment to see how suitable Haskell would be for machine learning related tasks. I am not planning on continuing work on this as there are very mature deep learning frameworks available nowadays.
- High speed due to hmatrix
- Multilayer perceptrons
- linear
- hyperbolic
- sigmoid
- Regression
- Backpropagation
- Datasets, I/O
- Softmax layer
- Classification
- Integrate with MNIST for illustration
- Modularization
- Convolutional neural networks
- Recurrent neural networks
- Backpropagation through time
- Long-short term memory
- ...