Hi Ralph. The correct link is http://www.cept.at
2013/8/21 Ralph Dratman <[email protected]> > www.cept.au is not responding > > > On Wed, Aug 21, 2013 at 2:38 PM, Jeff Hawkins <[email protected]>wrote: > >> Christian**** >> >> - Are there some researches related to HTM and NLP? Could indicate them? >> **** >> >> >> there have been several conversations on using NuPIC for NLP. Make >> sure to read these in the email archives. Also make sure to check out the >> Austrian company CEPT www.cept.au. Matt Taylor (NuPIC master of >> ceremonies) is looking at defining and posting some tasks and problems in >> the NLP space that might be suitable for NuPIC.**** >> >> ** ** >> >> ** ** >> >> - Is HTM proper to address this problem? Could it learn, without >> supervision, the grammar of a language or just help in some aspects as >> Named Entity Recognition? >> >> HTM is an overarching theory of neocortex, but NuPIC contains code >> that implements the equivalent of one layer of cells in one region. This >> is the CLA. The CLA has the promise of unsupervised learning of grammar. >> The key is starting with good SDR codings of words.**** >> >> Jeff >> **** >> >> **** >> >> Regards,**** >> >> Christian**** >> >> **** >> >> _______________________________________________ >> 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 > >
_______________________________________________ nupic mailing list [email protected] http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org
