Programming neural networks using Python?

I am a college student (economics) and I want to program some monetary models using Neural Networks. I want these models to be able to predict the future values โ€‹โ€‹of some variables using economic data, but I really don't know how to "model" the program itself. Is there a good Python module for this? I mean a module for NN and a module for economic analysis?

PS: I use Python 3.x, but if necessary I can switch to 2.7.x ...

+5
python neural-network models economics
source share
5 answers

There is also PyBrain . I have not worked with any library yet, but I had time to study the documentation. PyBrains seems to have the simplest interface compared to the available feature set.

EDIT I have (December 2010) some practical experience with PyBrain and, like him, very much.

+3
source share

I played a little with ffnet. PS - It was painful to install.

"Primary neural network for python"
http://pypi.python.org/pypi/ffnet/0.6

+2
source share

Google provides at least four different implementations of Python neural networks; in particular, bpnn.py looks just for simplicity.

Or were you looking for an explanation of neural networks?

+1
source share

For large neural networks, you might want to consider GPU accelerated libraries. Our own CUV library comes to mind, as well as, for example, theano . CUV has python bindings, theano actually generates C ++ / CUDA code.

+1
source share

pyfann, quickly and well documented: http://leenissen.dk/fann/wp/

0
source share

All Articles