Artemis aims to get rid of all the boring, bureaucratic coding (plotting, file management, organizing experiments, etc) involved in machine learning projects, so you can get to the good stuff quickly.
https://github.com/QUVA-Lab/artemis
I made a nice deep learning library called Plato. It’s built on top of Theano. Nobody uses it except me. But you should use it, because it’s really nice. A tutorial explaining what it is is here.
https://github.com/petered/plato
A small utility for exporting a script, along with all its dependencies, into a new GitHub repository.
https://github.com/petered/public-release
If you want to replicate the experiments in our recent paper, Deep Spiking Networks.
https://github.com/petered/spiking-mlp.
The Spiking MLP code relies on our Java library DeepSpike for running spiking neural networks. I wrote it in Java because it would run too slowly in Python, and our spiking networks can’t just be vectorized into numpy expressions.
https://github.com/petered/DeepSpike
Way back for my masters project I made another java spiking network library called JSpikeStack. It runs a pre-trained network of LIF Neurons as a Deep Belief Network.
https://sites.google.com/site/thebrainbells/home/jspikestack.