Hi Neil, you probably were not present at the last Hackathon in San Francisco. There I've seen with my own eyes how the CLA does the following things (list not exhaustive):
- controlling the altitude of a self flying toy helicopter - allowing a self driving car to learn it's environment and adjust its speed based on light ambiance - learning the sequence "animal" - "vegetable" based only on 4 or 5 lines of training material and then guessing an unknown vegetable based on the input of an unknown animal - powered by CEPT's semantic Word SDRs I can't comment on the implementation of the code but find the results quite impressive. As to performance metrics: The CEPT Word SDRs allow to measure how well the CLA is doing intuitively for humans because natural language can be the input and the output. So I suggest to keep an open mind and stay optimistic!! :-) All the best from Vienna, Daniel On Friday, January 10, 2014, Neal Donnelly wrote: > Hey everyone - > > I got involved with NuPIC with starry eyes after reading the CLA > whitepaper. The abstractions that it describes are exciting and the level > of work that was obvious in the codebase were very compelling. I was mildly > concerned that there were no results presented, but I was told that was > because there are no established metrics for measuring its performance > since it's so novel. > > Now, after mucking around in the network engine codebase for a while, I've > realized that the abstractions presented in the CLA whitepaper seem to have > little bearing on the implementation. Spatial and temporal pooling are > accomplished as separate types of regions, which are composed not of cells > but of Nodes, which are themselves comprised of elements...? > > This confusion has left me wondering why I believe in this project if > neither theory nor results back up the implementation. This line of > thinking has left me frustrated that I can't find a single result of NuPIC > actually *doing* anything. When none of the existing benchmarks are > fitting, researchers invent a new one. I realize I've seen no learning > curves, no applications to real data, no demonstrations of performance of > any kind. > > My hope is that this will provoke a flood of links and papers that I > missed. My fear is that I've been terribly naive to assume that NuPIC would > work when there aren't results out front and center. > > Thanks. > Neal Donnelly >
_______________________________________________ nupic mailing list [email protected] http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org
