Hi, If I read this correctly, what you have done here in essence is try to figure out the best possible parameter combination for the problem domain, like the swarm algorithm tries to do. I do not know exactly how the current swarm algorithm works except for the related expositional youtube video on Numenta's channel, but I intend to read the white paper to find out more. Thanks for sharing.
Ozgur On Fri, Jul 4, 2014 at 10:29 AM, Jim Bridgewater <[email protected]> wrote: > Hi everyone, > > I'm working on a NuPIC vision toolkit for the Season of NuPIC this > summer and I've created a GitHub repo for it called nupic.vision. The > URL is: > > https://github.com/baroobob/nupic.vision > > There is a demo for those who want to try it out. > > I've attached the write up of results from using this toolkit to > investigate the effects of the synapse connection threshold, > synPermConnected, the permanence increment for active synapses, > synPermActiveInc, and the permanence decrement for inactive synapses, > synPermInactiveDec, on image recognition accuracy and the amount of > training required. > > -- > Jim Bridgewater, PhD > Arizona State University > 480-227-9592 > > _______________________________________________ > nupic mailing list > [email protected] > http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org > >
_______________________________________________ nupic mailing list [email protected] http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org
