Mocha.jl: Deep Learning for Julia

Originally published at:

Deep learning is becoming extremely popular due to several breakthroughs in various well-known tasks in artificial intelligence. For example, at the ImageNet Large Scale Visual Recognition Challenge, the introduction of deep learning algorithms into the challenge reduced the top-5 error by 10% in 2012. Every year since then, deep learning models have dominated the challenges,…

This is beautiful. Is CUDA for Julia available now? I thought CUDA is only available for C/C++, Python, and Fortran according to this:

Because Julia has a foreign function interface, you can write and compile libraries that use CUDA in C/C++, and then call the libraries from Julia. Mocha.jl is written this way, but using Mocha.jl does not require you to write any CUDA kernels yourself.

You could also use this package as an easy wrapper to CUDA API

A list of related projects can be found here:

Is there a C++ binding for this?