Rust based Cross-GPU Machine Learning.
This project is for those that miss strongly typed compiled languages (where for-loops are okay!) Note: We still vectorize all the required BLAS tasks on the GPU.
- Multi GPU support
- OpenCL + CUDA + CPU build support
- Perceptron's
- Activations: [Sigmoid, Tanh, Softmax]
- Initializations: [Lecun Uniform, Glorot Normal, Glorot Uniform]
- Loss Functions: [MSE, Cross-Entropy]
- OpenGL based plotting
- AutoEncoder's [Work in Progress]
- LSTM's [Work in Progress]
- RTRL [Work in Progress]
See here
- Thanks to the arrayfire team for working with me to get the rust bindings up.
- Keras for inspiration as a lot of functions are similar to their implementation (minus the theano nonsense).