PyBrain: modular Machine Learning Library for Python

Python v. Ruby. The eternal question. The languages might not be different, but the communities definitely are.

This just convinced me I need to switch my efforts from Ruby to Python.

It seems like this would be a reasonable introduction to neural network programming (while PyBrain contains code for other classifiers, the site also suggests that this is mainly for comparative purposes). If you were more concerned about performance, it seems like it might be better to check out libfann.

I couldn't easily find comparative benchmarks, so this opinion is just based on the documentation of the two libraries and what they say about themselves. If I have some free time this week (hah!) I'll throw together a quick and dirty performance comparison.

I wish I had that 2 years ago in university :) It seems well coded, the documentation is clear and concise and it's in python! Overall, a cute library that I will certainly add to my bag.

I have two small concerns thought:

1- "Only forward"

2- Possibility to expend it.. For instance, what if I want to evolve my neural network with a genetic algorithm, is this possible? And if so, how easy it is?

I tried this out about a year ago while at college. The dependencies were very painful and I was never able to install it.

I would love to know if anyone has this running on Mac OS X successfully now. I'd love to check it out, but had a terrible experience last time I tried it.

It would be nice to see a neural network learning how to land a plane safely... even with crosswind. I think it'd be able to pull that off.

Does it work on Google App Engine?

One step closer to being able to simply put "import soul" at the top of my scripts.