New Ideas About Temporal Pooling(github.com)
github.com
New Ideas About Temporal Pooling
https://github.com/numenta/nupic/wiki/New-Ideas-About-Temporal-Pooling
1 comments
From what I've observed, quite a few people on HN have read "On Intelligence" and are receptive to these type of posts.
I'm guessing this is the same Scott that gave the presentation at OsCon? I wasn't physically there, but watched it online. It was one of my early exposures to NuPic, CLA, HTM, Jeff Hawkins, etc. Thanks for that.
Have you had a chance to play around with NuStudio (by David Ragazzi)? I don't think I've seen you comment on it via the mailing list.
I'm guessing this is the same Scott that gave the presentation at OsCon? I wasn't physically there, but watched it online. It was one of my early exposures to NuPic, CLA, HTM, Jeff Hawkins, etc. Thanks for that.
Have you had a chance to play around with NuStudio (by David Ragazzi)? I don't think I've seen you comment on it via the mailing list.
Thanks Michael and Scott for try NuPIC Studio!
This weekend I'll update NuStudio repo with the newest version and its tutorial..
This weekend I'll update NuStudio repo with the newest version and its tutorial..
Yes same Scott. Unfortunately my first installation attempt for NuStudio was unsuccessful but I will try again soon. David has been very involved and it is great to see projects like that that make it more accessible.
> The basic idea of temporal pooling is patterns that occur adjacent in time probably have a common underlying cause and therefore the brain forms a stable representation for a series of input patterns.
While the idea is simple, the implementation is tricky. We recently made our experimentation public here: https://github.com/numenta/nupic.research
Jeff also had a really informal discussion about the topic at one of our hackathons: http://numenta.org/blog/2014/05/09/2014-spring-hackathon-out...