Hi, Can we ask Jeff to post his detailed new ideas about layers in context of sensory-motor integration? In his video he skip the topic about this, but I think it's very important for all of us. Please tell us where we can find this information if there is any or whet it will be published. Also there is a promise in CLA white paper about updates to it according to progress in implementation. When it will be updated to reflect current status of theory basis and actual implementation?
With best regards, Maxim Krymchak On Fri, May 2, 2014 at 7:00 PM, <[email protected]> wrote: > Send nupic mailing list submissions to > [email protected] > > To subscribe or unsubscribe, visit > http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org > or, via email, send a message with subject or body 'help' to > [email protected] > > You can reach the person managing the list at > [email protected] > > When replying, please edit your Subject line so it is more specific > than "Re: Contents of nupic digest..." > > > Today's Topics: > > 1. Re: nupic Digest, Vol 12, Issue 78 (Matthew Taylor) > 2. Re: PROPOSAL: Drop Python 2.6 support for NuPIC (Matthew Taylor) > > > ---------------------------------------------------------------------- > > Message: 1 > Date: Thu, 1 May 2014 21:27:11 -0700 > From: Matthew Taylor <[email protected]> > To: "NuPIC general mailing list." <[email protected]> > Subject: Re: [nupic-discuss] nupic Digest, Vol 12, Issue 78 > Message-ID: > <CAJv6nDNoCgWmFpYYe9rHbF=DvRaGoOZGtmqWT9H7MT= > [email protected]> > Content-Type: text/plain; charset=UTF-8 > > Magnus, thanks for the message. But I think it would fit better in the > nupic-theory mailing list. > > http://lists.numenta.org/mailman/listinfo/nupic-theory_lists.numenta.org > > Regards, > --------- > Matt Taylor > OS Community Flag-Bearer > Numenta > > > On Thu, May 1, 2014 at 9:08 PM, Magnus McWootton <[email protected]> > wrote: > > I just had a thought, and its do with the hierarchy, and inference, and > > spacial pooling. > > > > when you are inferring, you wind up, every symantic, a percentage error, > > coming up the proximals, > > you can use a threshold to instantly activate it at some error. but > > wouldnt it be better, if you just passed up the error? > > it works better this way, because then your smaller groups will work > better, > > because they dont get stuck at an error minima. > > the later symantics can then "continuify" the error to a more exact > > quotient, by reading the error of the previous level, using > > the errors together to make a new error, which would have less error than > > the previous level, most of the time. > > > > then you could keep passing the error till the last region, then have an > > exact "nearness" to the novel input > > using every single symantic together, leaving activation till later, > making > > use of the distribution together. > > > > notes about my system-> > > Its purely spacial, with no temporal yet, that makes this idea much > easier > > to do. i also finish at a single > > collection, so all i have to do to inference is pick the cell of least > > error. and it also has a separate inferencing stage from training > > so i dont know if this idea applies to htm, but possibly could be > useful > > to know. > > > > > > _______________________________________________ > > nupic mailing list > > [email protected] > > http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org > > > > > > ------------------------------ > > Message: 2 > Date: Fri, 2 May 2014 07:32:04 -0700 > From: Matthew Taylor <[email protected]> > To: "NuPIC general mailing list." <[email protected]> > Subject: Re: [nupic-discuss] PROPOSAL: Drop Python 2.6 support for > NuPIC > Message-ID: > < > cajv6ndnbfo8yps4z92r1uc95esirxoz9qty1qo+364cem-u...@mail.gmail.com> > Content-Type: text/plain; charset=UTF-8 > > We've got to get builds running once again, and Austin has a PR [1] > that does this, but removes Python 2.6 support. We usually give > proposals like this 72 hours, but I'm going to push the merge button > so we can get our pipeline unclogged. Pull requests are backing up. > > If anyone reading this really needs Python 2.6 support, let's continue > the discussion about adding it back in. But in the meantime, we've > moving forward with this proposal. > > [1] https://github.com/numenta/nupic/pull/906 > > Regards, > --------- > Matt Taylor > OS Community Flag-Bearer > Numenta > > > On Thu, May 1, 2014 at 2:37 PM, Archie, Kevin <[email protected]> > wrote: > > Mac OS X has shipped with 2.7 since Lion (2 major versions ago, July > 2011) > > and it's reasonably straightforward to put 2.7 on earlier releases. > > > > - Kevin > > > > > > > > On May 1, 2014, at 3:46 PM, Subutai Ahmad wrote: > > > > > > I believe most unix OS's still ship with Python 2.6.x out of the box - is > > that right? If so, people will need to install 2.7 before using NuPIC. > As > > long as that is OK, I'm +1 for this. > > > > --Subutai > > > > > > On Thu, May 1, 2014 at 12:32 PM, habib valanejad < > [email protected]> > > wrote: > >> > >> Hello, > >> > >> The latest version of Python on Solaris is 2.6.8 . > >> Regarding Solaris port, I'm looking forward to discuss this matter with > >> you guys on Saturday. > >> > >> Regards, > >> Habib > >> > >> > >> On 05/01/2014 11:44 AM, Marek Otahal wrote: > >> > >> +1 ,although I'd like to hear about other "platforms" first - Solaris > >> recently, ... > >> > >> > >> On Thu, May 1, 2014 at 8:16 PM, Ian Danforth <[email protected]> > >> wrote: > >>> > >>> +1 > >>> > >>> > >>> On Thu, May 1, 2014 at 11:03 AM, Austin Marshall <[email protected]> > >>> wrote: > >>>> > >>>> +1 for deprecating 2.6. Though, I'd be perfectly happy if someone > took > >>>> on the role of supporting 2.6 as-needed. > >>>> > >>>> > >>>> On Thu, May 1, 2014 at 10:55 AM, Matthew Taylor <[email protected]> > >>>> wrote: > >>>>> > >>>>> This means we would drop our Python 2.6 builds from the Travis-CI > >>>>> matrix and remove python 2.6 packages from our support repos [1][2]. > >>>>> NuPIC would only support Python 2.7. > >>>>> > >>>>> If you are using NuPIC with Python 2.6 and are unable or unwilling to > >>>>> upgrade to Python 2.7, this is your chance to speak up. > >>>>> > >>>>> Pros: This would significantly decrease NuPIC build loads within our > >>>>> continuous integration environment, de-complicate our builds, and > make > >>>>> it easier for us to support installation. > >>>>> > >>>>> Cons: NuPIC would only support Python 2.7. > >>>>> > >>>>> This discussion came up while we were figuring out how to handle > >>>>> recent Travis-CI failures [3]. > >>>>> > >>>>> [1] https://github.com/numenta/nupic-linux64 > >>>>> [2] https://github.com/numenta/nupic-darwin64 > >>>>> [3] https://github.com/numenta/nupic/issues/901 > >>>>> > >>>>> --------- > >>>>> Matt Taylor > >>>>> OS Community Flag-Bearer > >>>>> Numenta > >>>>> > >>>>> _______________________________________________ > >>>>> 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 > >>> > >> > >> > >> > >> -- > >> Marek Otahal :o) > >> > >> > >> _______________________________________________ > >> 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 > > > > > > > > ________________________________ > > > > The material in this message is private and may contain Protected > Healthcare > > Information (PHI). If you are not the intended recipient, be advised that > > any unauthorized use, disclosure, copying or the taking of any action in > > reliance on the contents of this information is strictly prohibited. If > you > > have received this email in error, please immediately notify the sender > via > > telephone or return mail. > > > > _______________________________________________ > > nupic mailing list > > [email protected] > > http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org > > > > > > ------------------------------ > > Subject: Digest Footer > > _______________________________________________ > nupic mailing list > [email protected] > http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org > > > ------------------------------ > > End of nupic Digest, Vol 13, Issue 3 > ************************************ >
_______________________________________________ nupic mailing list [email protected] http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org
