SFML community forums

General => SFML projects => Topic started by: lolz123 on November 11, 2014, 01:58:48 am

Title: SFML GPU-CHTM
Post by: lolz123 on November 11, 2014, 01:58:48 am

Hello!

I have recently been working on some hierarchical temporal memory (HTM) stuff, and developed my own variant called continuous HTM (CHTM).

HTM is an algorithm for simulating the functions of the neocortex.

My CHTM implementation performs reinforcement learning (learning towards a goal). It runs entirely on the GPU using OpenCL.

I made a visualization of my CHTM using SFML's graphics system. It is essentially a volume renderer, composed of many stacked 2D slices. It doesn't use raw OpenGL, since I didn't need it (I wanted an orthographic projection).

Here is a video of the cortical tissue volume in action. It isn't shown in the video, but the system is learning to balance a pole.

https://www.youtube.com/watch?v=OrnYkTLqV6w (https://www.youtube.com/watch?v=OrnYkTLqV6w)

As usual, it is free open source software. It is available here: https://github.com/222464/ContinuousHTMGPU (https://github.com/222464/ContinuousHTMGPU)

For those who want to learn more about HTM, you can read the following paper: http://numenta.org/resources/HTM_CorticalLearningAlgorithms.pdf (http://numenta.org/resources/HTM_CorticalLearningAlgorithms.pdf)

Title: Re: SFML GPU-CHTM
Post by: josh123 on November 13, 2014, 10:01:41 pm

Awesome dude, really nice work. I got interested in Jeff Hawkins's stuff like a month ago. Cool to see it extensions being made.