[oelmekki]

I think the key factor here has been numpy, the scientific library for python. Academics used python because of it, and they are the ones who wrote the neural networks tooling.

We probably can expect to see implementations in all languages at some point. Floating point errors are not even that a big deal since we're dealing with statistics anyway.

That being said, neural networks are very resource/computation heavy. I wrote one in golang and cut my execution time in half just by encoding my matrices as flat arrays instead of two dimensional arrays. If ruby is to be used to build neural networks, it will need to perform the big work in a binary binding, like tensorflow does with its C++ layer.

[matt4077]

I doubt that anybody is thinking of actually running the networks in ruby, or python, or even C on the GPU. They're all run on the GPU anyway.