Home

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: Hacky code there. Getting it to compile is difficult (moving directories, etc), and currently pointless without modifying the code as it’s in the state I left it after running experiments. It’s got lots of hard coded values, now unused code, explicit file paths, it’s all in one file shudder. Still, if you want to see the basic idea then it’s there. I’ll be improving it and making it a lot more flexible, it currently doesn’t allow fine grained control of parameters during training (which I now want to experiment with).

If you have any questions, or want to try and compile it, then feel free to drop me an email and I’ll help out best I can.