cedricblack

In a way that's what nature does :) I think this combination is quite common.

While visiting a lab in Paris, I saw some researchers using neuroevolution to teach a bird-like robot how to fly.

some links related to neuroevolution:

https://en.wikipedia.org/wiki/Neuroevolution_of_augmenting_t...

http://eplex.cs.ucf.edu/hyperNEATpage

https://github.com/colgreen/sharpneat

It is a using a genetic algorithm so learning lies in the mutation and crossover of chromosomes as well as selection of the fittest individuals.

https://github.com/xviniette/FlappyLearning/blob/gh-pages/Ne...

Thanks for the tip. I'll see where I can apply it.

Most of the time is usually spent in the convolution layers. Convolution is not a matrix multiplication in the current implementation. I guess it would be a matrix multiplication in frequency domain or by using a Toeplitz matrix.

I've implemented a CPU Parallel version and gave a try at GPU implementation. But I'm not satisfied at all by the GPU version :)

https://github.com/cbovar/ConvNetSharp/blob/master/src/ConvN...

https://github.com/cbovar/ConvNetSharp/blob/Gpu/src/ConvNetS...

Pull requests more than welcome!

I ported ConvNet JS to C# in order to really understand what's going on: https://github.com/cbovar/ConvNetSharp