Skip to content
IanCal edited this page Sep 13, 2010 · 6 revisions

Info:

This is a placeholder at the moment. However, the project is an implementation of Restricted Boltzmann Machines on the GPU, specifically in CUDA.

Acronym-tastic.

It started as a research project, to see if it was a decent idea and to explore the various variables. Turns out, yeah, it is. Unfortunately for standard problems you need to batch a lot of work together (my old 8600GT required 32 images at a time on a 784-512-512-2048 network to get a 10-50x speedup). However, as work progresses onto larger networks (for such things as fMRI, or perhaps multi-scale/attribute images) it seems pretty useful.

Current status: Empty. There should be something decent here by March.

Clone this wiki locally