Neural Network primitives with multiple backends
Author FluxML
99 Stars
Updated Last
2 Years Ago
Started In
August 2017


Build Status Build status Coverage Documentation

This package will provide a library of functions useful for ML, such as softmax, sigmoid, convolutions and pooling. It doesn't provide any other "high-level" functionality like layers or AD.

Other packages can build on these functions as if they were defined in Base Julia; for example, CUDA.jl provides GPU kernels, and Zygote.jl provides automatic differentiation; both can work together without explicitly being aware of each other.