Connectionists: open-source for massively parallel neural encoding/decoding of visual stimuli/scenes

[Aurel A. Lazar]

Source code for encoding and decoding of natural and synthetic  visual scenes (videos) with
Time Encoding Machines consisting of Gabor or center surround  receptive fields in cascade
with Integrate-and-Fire neurons is available at  http://www.bionet.ee.columbia.edu/code/vtem
The code is written in Python/PyCuda and runs on single GPUs.

The current release supports grayscale videos. Stay  tuned for color and multi-GPUs implementations.

A visual demonstration of decoding a short video stimulus encoded  with a Video Time Encoding Machine
consisting of 100,000 Hodgkin-Huxley neurons is available at:  http://www.bionet.ee.columbia.edu/research/nce

Aurel
http://www.bionet.ee.columbia.edu/



-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/connectionists/attachments/20130614/883dea62/attachment.html>