Chris, Thanks for posting this, very interesting work. I have been trying to think of ways to connect machine learning to chemistry/materials science, so its very interesting to see the approach these guys have taken. I haven’t read the paper in detail, but it seems like they are dealing with on the order of 50 species with 100 reactions. It seems to me the size of this reaction system would be extremely difficult to implement in a controllable way. As they note, they do not deal with how small errors in measuring out different amounts of chemicals will affect the system. In addition, I don’t see that they are considering issues of cross-reactivity. My intuition is that if you put 50 species together, cross-reactivity is going to give you at a minimum thousands of reactions. Maybe there is a way to define the reactions to be more specific, but I don’t know of any system that does something like they are doing with their math.
Best, Ben Dept of Chemistry Duke University On Feb 6, 2014, at 11:38 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: Tests for spatial pooling (Dean Horak) > 2. Intelligent Chemicals (Chris Jernigan) > 3. Re: Intelligent Chemicals (Chris Jernigan) > 4. Re: Congrats Jeff (Erik Blas) > 5. Re: First commercial product built on NuPIC (Erik Blas) > 6. Re: Congrats Jeff (Jeff Fohl) > 7. Re: Congrats Jeff (Teri Fry) > > > ---------------------------------------------------------------------- > > Message: 1 > Date: Thu, 6 Feb 2014 17:05:31 -0600 > From: Dean Horak <[email protected]> > To: "NuPIC general mailing list." <[email protected]> > Subject: Re: [nupic-discuss] Tests for spatial pooling > Message-ID: > <CAPW5hGCES6mQ6YdN_oG0=hqipmi5x4z4mq3ej60gvl+km6p...@mail.gmail.com> > Content-Type: text/plain; charset="iso-8859-1" > > Hi Jeff, > > I certainly didn't mean to imply you weren't able to discuss the issues at > a more detailed level, as I know very well you are. I was primarily > referring to the discussion in this thread about the visual system. As you > noted, V1 is organized in a topographical fashion and this is true, but > there is so much more to it than that, and what there is provides key > insights into how it does what it does. > > For instance: > > The optic nerve from each eye pass through the optic chiasm, where a > portion of the axons decussate and project to the posterior thalamus (LGN). > However, a portion of the axons do not decussate, and instead project to > the LGN on the ipsilateral side. The axons that decussate project into > layers 1,4 and 6 of the LGN, while the axons that do not decussate project > to layers 2,3 and 5. The LGN then projects output from these layers into > layer 4 of separate cortical columns in V1. This forms an interdigitative > pattern of columns in V1 (called ocular dominance columns). Up until this > point (in layer 4) the signals from each eye is monocular. It is only when > layer 4 of V1 projects to upper layers (2 and 3) that the signals become > mixed for the first time, which makes stereopsis possible. Note that this > implementation is very different than most stereo computer vision schemes > and explains why when we close one eye the world does not colllapse into > 2D. Those less dominant columns continue to become active, though at lower > efficiency, allowing us to retain diminished, but very real 3D vision in > spite of lack of input from one eye. > > Within the V1 within each "pinwheel" associated with each receptive field, > there is a fairly consistent organization of columns. Certain columns are > selective for specific orientation (orientation selectivity), while > surrounding these columns are columns which are selective for direction > (direction selectivity). Also, we know that orientation selectivity is > driven by genetics, while direction selectivity is driven by learning. > > Additionally, the axons coming into the LGN consist of parallel pathways. > The LGN receives input from M-ganglion cells into layers 1 and 2 > (magnocellular layer), P-ganglion Cells into layers 3-6 (parvocellular > layers), and K-ganglion Cells in between each M and P cell layer. The M and > P cells then project to V1 layer 4 (M cells to layer 4C beta and P cells to > layer 4C alpha), but K cells project directly to layers 2 and 3 forming > "blobs" (which are especially rich in enzymatic activity for oxidative > metabolism). > > The parvocellular layer is thought to be concerned with form, spatial > detail and color. The magnocellular layer is concerned with broad patterns > of motion. It is thought these blobs play a role in color vision, though > this is still not well understood. > > My point in all of this is that that there is so much rich information that > is simply missed if we simply describe V1 as a pattern of pixels. How much > of this detail needs to be taken into account in designing the CLA is an > open question, but I think if we design around an overly simplistic > description we wind up with a design that falls short of biology. We should > at least be aware of as much detail as we have at our disposal when making > design decisions to arrive at the most robust implementation possible. > > I watched this happen decades ago when ANNs were all the rage. While they > were somewhat biologically inspired, they missed so much detail about how > real neurons worked that they were never able to rise to the level of their > hype and only now, as they are coerced into more accurate representations, > are we seeing progress. > > I hope this message at least give you some idea where I'm coming from and > while I was asking about more neuroscience based discussions. > > Dean > > > On Thu, Feb 6, 2014 at 3:34 PM, Jeff Hawkins <[email protected]> wrote: > >> Dean. >> >> Your comment made me smile! This is the first time anyone has said I work >> at the 10,000 foot level of neuroscience! My problem is always the >> opposite. >> >> >> >> The theory and models we work on are by most standards very biological. >> For example, I know of no other cortical theories/models that incorporate >> any of the following, active dendrites, differences between proximal and >> distal dendrites, synapse growth and decay, potential synapses, dendrite >> growth, depolarization as mode of prediction, mini-columns, multiple types >> of inhibition and their corresponding inhibitory neurons, etc. The new >> temporal pooling mechanism we are working on requires metabotropic >> receptors in the locations they are, and are not, found. Again, I don't >> know of any theories that have been reduced to practice that incorporate >> any, let alone all of these concepts. The machine learning community in >> general is ignorant of any of these kinds of details. >> >> >> >> One of the things I struggle with is how to describe the algorithms >> without the neuroscience. Most people are unfamiliar with the biological >> terms and concepts. But I am very happy to discuss them on this forum. >> >> >> >> Jeff >> >> >> >> >> >> *From:* nupic [mailto:[email protected]] *On Behalf Of *Dean >> Horak >> *Sent:* Thursday, February 06, 2014 11:31 AM >> >> *To:* NuPIC general mailing list. >> *Subject:* Re: [nupic-discuss] Tests for spatial pooling >> >> >> >> Great thanks. I'll do just that. >> >> >> >> Dean >> >> >> >> On Thu, Feb 6, 2014 at 1:28 PM, Matthew Taylor <[email protected]> wrote: >> >> Dean, >> >> >> >> This mailing list is entirely appropriate for those types of discussions. >> If you have a specific topic or question, please feel free to start a new >> conversation. >> >> >> --------- >> >> Matt Taylor >> >> OS Community Flag-Bearer >> >> Numenta >> >> >> >> On Thu, Feb 6, 2014 at 11:25 AM, Dean Horak <[email protected]> wrote: >> >> This may be a little off topic for this thread, but is there a proper >> place for discussions regarding neuroscience and how the CLA does or does >> not approach problems the way biology does? I bring this up here because >> while Jeff's comments are indeed correct, they are at a 10,000 ft level. It >> seems to me there are many insights that might well prove useful within the >> CLA that can be derived from discussions of neuroscience at a much deeper >> level. >> >> >> >> Thanks, >> >> Dean >> >> >> >> On Thu, Feb 6, 2014 at 8:30 AM, Christian Cleber Masdeval Braz < >> [email protected]> wrote: >> >> >> Kevin, i think i understood better the relation between inhibition and >> topology. If topology is taking into account, so the position of the input >> bits matter. In this case, the sub set of bits each column will "look" are >> not random but organized somehow. For an image, the first column will be >> connected to the first n bits (or some 2D portion in the beginning of the >> image), the second will be connected to the adjacent bits and so on. In >> this case, local activity and the job of inhibition makes sense to >> guarantee sparsity and distribution. >> >> On the other hand, if no topology exist, there is no difference in use >> inhibition or not. Will be ok in choosing the columns with the highest >> overlap values because each of them will be looking an aleatory sub set of >> bits spread all over the input. So, even if happens what you described, the >> resulting columns will have a good distribution. >> >> Regards, >> >> Christian >> >> >> >> >> >> 2014-02-06 Kevin Martin <[email protected]>: >> >> >> >> Thanks everyone, >> >> >> >> The term topology is very clear to me now. But in Fergal's explanation, he >> had said that >> >> >> "In the absence of topology, it's more efficient to just pick the highest >> activation potentials globally" >> >> But this means a distributed representation is not guaranteed right? >> Suppose we had 1000 columns and 200 input bits and desired sparsity is 1% >> (10 columns). Each column is potentially connected to say 75% of the input >> bits. Let the inhibition radius be 20 and desiredlocalactivity 5. Even >> though it is very unlikely, let us assume that 10 columns with the highest >> overlap values occur within a particular inhibition radius. >> >> That is, if the highest 11 overlap values are 125,124,122,....115 (for the >> sake of simplicity) in the entire layer, and the columns that have these >> values are ordered like this : >> >> x x 125 120 x 119 115 x 118 123 Y x x 121 122 x 116 x 117 x 124 >> >> Where x and Y are unknown overlaps. In this case, the inhibition radius of >> Y contains all the top 11 overlaps. Without inhibition, the columns with >> overlaps 125,124,123,122,121...116 will be the winners to give us the 1% >> sparsity. They all occur together. But with inhibition only 5 columns will >> be winners here and the other 5 will come from a different part of the >> layer. So even though just getting the columns with the highest overlaps is >> way more easier and efficient, will it not result in a higher chance of >> getting a representation that is not very distributed? >> >> Thanks, >> >> Kevin Martin Jose >> >> >> >> On Thu, Feb 6, 2014 at 6:33 AM, Fergal Byrne <[email protected]> >> wrote: >> >> Thanks Jeff, >> >> >> >> Perhaps the difficulty arises from the disparity between cortex (which >> just is as it is) and a realisation in software. Neurons can only operate >> locally, and their computation depends on the topology of the axons passing >> by them. >> >> >> >> In NuPIC, we can design both the topology of the neurons' inputs and also >> the inhibition strategy. >> >> >> >> I think Kevin is asking about the semantics of topology (and >> sparseness/distribution) in that sense. >> >> >> >> Regards, >> >> >> >> Fergal Byrne >> >> -- >> Sent from Mailbox <https://www.dropbox.com/mailbox> for iPhone >> >> >> >> On Thu, Feb 6, 2014 at 12:52 AM, Jeff Hawkins <[email protected]> >> wrote: >> >> I hope to clarify what topology is. I agree with some of what Fergal >> wrote but disagree with other parts, so maybe we are thinking different >> things. >> >> >> >> In a brain, the cortex is a sheet of tissue. Everywhere you look, it is >> about 2mm thick and consists of 4 or 5 layers of cells (depends on how you >> count). The total area of human neocortex is about 1000 cm2. Cortical >> regions are 2D areas. Some of the regions, such as the primary visual or >> touch regions are large. The retina sends about a million axons to the >> primarily visual cortex, or V1. Each axon represents a small part of the >> visual space, sort of like a pixel in an image. When this bundle fibers >> reaches V1 the 2D topology of the axons is maintained. It is as if a 1M >> pixel image were projected on to the area of V1. (The "image" is inverted, >> split, and highly distorted, but in all cases any two adjacent areas of V1 >> receive input from adjacent areas of the retina.) Scientists would say V1 >> has a "retinotopic" orientation. >> >> >> >> Now comes the interesting part. The cells in V1 learn common patterns >> coming from the retina. The way the SP works is each bit in the SP tries >> to learn the largest spatial pattern it can. And each bit competes with >> the other bits. The number of patterns coming from the retina is so large >> that the SP bits are forced to learn only small spatial patterns that are >> localized on the retina. So cells on the right side of V1 learn small >> patterns on the left side of the retina (remember the image is inverted). >> In biological V1 all the learning rules are local. Inhibition between >> columns is restricted in radius. The axons that a cell can possibly >> connect to are restricted to a radius. >> >> >> >> When we say a region has topology it means that inhibition between columns >> is limited to a local radius and not the entire region. It means that the >> set of potential connections that a cell or column can make are also within >> a radius and not all possible input bits or all possible cells in the >> region. This is the way real neocortex works. When we were applying the >> CLA to vision-like problems we implemented it with topology. It worked as >> expected but it is more complicated to test. The current implementation of >> the CLA has no topology. This means that each column competes with all the >> other columns and the set of potential connections between cells is a >> subset of all the cells in the region. There is no ordering of the >> columns, nothing is "adjacent" to anything else. For applications that are >> small no topology works great. If the application had a large 2D sensory >> array then topology would likely be required. >> >> >> >> I hope that helped. >> >> Jeff >> >> >> >> *From:* nupic [mailto:[email protected]] *On Behalf Of *Fergal >> Byrne >> *Sent:* Wednesday, February 05, 2014 5:54 AM >> *To:* NuPIC general mailing list. >> *Subject:* Re: [nupic-discuss] Tests for spatial pooling >> >> >> >> HI Kevin, >> >> >> >>>> The following ideas are not things I think relate to "topology". >> >> >> >> Topology is the jargon we use to describe the semantic meaning (or lack of >> it) of a column (or input bit) position, and for connections between them. >> >> For example, a typical encoding of category data randomly picks 21 bits on >> out of 128. Each bit position has no real connection with the input >> category it encodes. This representation has no topology at all. >> >> Conversely, the sliding window of on-bits in a scalar encoding has >> one-dimensional topology. In this case, bit 0 might mean the input is < 10, >> while bit 23 might mean an input between 11 and 33. >> >> >> >>>> These ideas are things I think relate to "topology". >> >> >> >> An example of a 2d topology in an SDR is a retina-like sensor. In this >> case the light levels or presence of particular features in a certain >> spatial position would be represented by bits in the corresponding position. >> >> Topology in the SP relates to how each column position is connected with >> its input bits. An SP which is learning to recognise features in an SDR >> coming in from a retina would have columns "looking at" a set of input bits >> directly "below it" in the retina. The V1 primary visual cortex has exactly >> this property. >> >> If you have topology, you'll usually use local inhibition to pick winning >> columns, where local is defined according to the topology (1-d, 2-d >> distance). In the absence of topology, it's more efficient to just pick the >> highest activation potentials globally. >> >> >> >> Regards >> >> >> >> Fergal Byrne >> >> >> >> >> >> >> >> On Wed, Feb 5, 2014 at 11:25 AM, Kevin Martin <[email protected]> >> wrote: >> >> Hi all, >> >> Thanks for the help. But I'm not sure if I understand what you mean by >> topology. As far as I understand, the spatial pooler has 2 functions : >> Return a set of columns that are 1)sparse and 2)distributed. >> >> Sparsity can be maintained by making sure that the pooler returns only n% >> of columns and this criterion can be made into a test. And distribution can >> be tested by computing the average distance between winning columns. What >> is topology? Is it another way of referring to a distributed set of >> columns? I might need some help with local learning too. I'm afraid I have >> never heard the term before (its in the white paper? A quick search on the >> pdf did not see any hits for "local learning") >> >> Thanks, >> >> Kevin Martin >> >> >> >> On Wed, Feb 5, 2014 at 7:37 AM, Scott Purdy <[email protected]> wrote: >> >> I would go over the properties of the SP and create tests accordingly. The >> output, for instance, should be tolerant to spatial noise. So show an >> instance a set of very different spatial patterns over and over a number of >> times. Then show one of the patterns with a single bit flipped and make >> sure the output is very close (possibly identical if columns are saturated) >> to the same. >> >> There are a bunch of similar things you could check. >> >> Ian had a hackathon demo showing the connected bits for each column. He >> was able to validate different aspects of the SP visually by using >> different numbers of columns and % overlap. >> >> You could do something similar to make sure you see the right behavior but >> I don't know if you could make an automated test out of it. >> >> >> http://numenta.org/blog/2013/11/06/2013-fall-hackathon-outcome.html#sp_viewer >> >> On Feb 4, 2014 11:23 AM, "Jeff Hawkins" <[email protected]> wrote: >> >> Kevin, >> >> Adding on to what Fergal said.... >> >> >> >> Here is what we did. We started with a fixed number of columns and no >> topology. In this situation we picked the n% most innervated columns as >> the output of the SP. Thus we were *guaranteed* to get the correct >> sparsity of active columns. With this setup we did a lot of other tests to >> verify that the SP was forming good representations. >> >> >> >> The tricky part is if you want to do this with topology and local learning >> rules. Is that your concern? >> >> >> >> With topology we didn't try to guarantee the entire layer of cells will >> have exactly n% active columns. Exact numbers are not essential. We tried >> several different local learning rules, all of them produced about the >> right level of sparsity. We than ran the other tests to make sure that >> local learning rules didn't cause the SP to form poor representations. You >> won't get exactly the same results with topology and without topology but >> my recollection was we were able to come up with a set of local inhibition >> rules that produced good results. >> >> Jeff >> >> >> >> *From:* nupic [mailto:[email protected]] *On Behalf Of *Fergal >> Byrne >> *Sent:* Tuesday, February 04, 2014 10:43 AM >> *To:* NuPIC general mailing list. >> *Subject:* Re: [nupic-discuss] Tests for spatial pooling >> >> >> >> Hi Kevin, >> >> >> >> If you're using no topology (and no local inhibition) then the fraction of >> active columns (2% in NuPIC) is the only important factor. With topology, >> you should choose winners relative to their neighbours. In either case, the >> first test is to count the fraction of active columns. In the second case, >> measure the average distance between active columns. >> >> >> >> Regards, >> >> >> >> Fergal Byrne >> >> >> >> On Tue, Feb 4, 2014 at 6:05 PM, Kevin Martin <[email protected]> >> wrote: >> >> Hi, >> >> I'm writing my own version of the CLA. I have not reached anywhere >> significant and I have been playing with a very small number of columns >> until now. I am starting by implementing a spatial pooler and spatial >> pooling requires a large number of columns. So far it has been easy to >> manually check if the synapses are distributed throughout the input, if the >> winning columns are really sparse etc. But it is going to be impossible >> when, say,I use 1000 columns. Have somebody used a test to check if the >> spatial pooler outputs a sparse distribution? Any suggestions on how to >> write a test? >> >> Thanks, >> >> Kevin Martin Jose >> >> >> _______________________________________________ >> nupic mailing list >> [email protected] >> http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org >> >> >> >> >> >> -- >> >> >> Fergal Byrne, Brenter IT >> >> >> >> http://inbits.com - Better Living through Thoughtful Technology >> >> >> >> e:[email protected] t:+353 83 4214179 >> >> Formerly of Adnet [email protected] http://www.adnet.ie >> >> >> _______________________________________________ >> 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 >> >> >> >> >> >> -- >> >> >> Fergal Byrne, Brenter IT >> >> >> >> http://inbits.com - Better Living through Thoughtful Technology >> >> >> >> e:[email protected] t:+353 83 4214179 >> >> Formerly of Adnet [email protected] http://www.adnet.ie >> >> >> >> >> _______________________________________________ >> 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 >> >> >> >> >> _______________________________________________ >> 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 >> >> > -------------- next part -------------- > An HTML attachment was scrubbed... > URL: > <http://lists.numenta.org/pipermail/nupic_lists.numenta.org/attachments/20140206/63ac8c58/attachment-0001.html> > > ------------------------------ > > Message: 2 > Date: Thu, 6 Feb 2014 18:57:32 -0500 > From: Chris Jernigan <[email protected]> > To: "NuPIC general mailing list." <[email protected]> > Subject: [nupic-discuss] Intelligent Chemicals > Message-ID: <[email protected]> > Content-Type: text/plain; charset=us-ascii > > They are doing some really cool research at Harvard on using chemical > reactions to create intelligent systems. Here is the article: > http://www.seas.harvard.edu/news/2013/12/programming-smart-molecules > > And a PDF of the original paper here: > http://papers.nips.cc/paper/4901-message-passing-inference-with-chemical-reaction-networks.pdf > > Most of the math is way beyond me, but the concept seems solid enough. What > do you guys think? > > -Chris > > > ------------------------------ > > Message: 3 > Date: Thu, 6 Feb 2014 19:07:52 -0500 > From: Chris Jernigan <[email protected]> > To: "NuPIC general mailing list." <[email protected]> > Subject: Re: [nupic-discuss] Intelligent Chemicals > Message-ID: <[email protected]> > Content-Type: text/plain; charset=us-ascii > > I forgot to ask, do you think this could be used to implement an efficient > HTM? > > On Feb 6, 2014, at 6:57 PM, Chris Jernigan <[email protected]> > wrote: > >> They are doing some really cool research at Harvard on using chemical >> reactions to create intelligent systems. Here is the article: >> http://www.seas.harvard.edu/news/2013/12/programming-smart-molecules >> >> And a PDF of the original paper here: >> http://papers.nips.cc/paper/4901-message-passing-inference-with-chemical-reaction-networks.pdf >> >> Most of the math is way beyond me, but the concept seems solid enough. What >> do you guys think? >> >> -Chris > > > > > ------------------------------ > > Message: 4 > Date: Thu, 6 Feb 2014 19:19:15 -0800 > From: Erik Blas <[email protected]> > To: "NuPIC general mailing list." <[email protected]> > Subject: Re: [nupic-discuss] Congrats Jeff > Message-ID: > <CAHmtO-zmNdFc8t7_zwQGrb62wpa4i+qTw5=gtx6amio81kd...@mail.gmail.com> > Content-Type: text/plain; charset="iso-8859-1" > > Beautiful child! > > > On Fri, Jan 31, 2014 at 1:04 PM, Subutai Ahmad <[email protected]> wrote: > >> Beautiful baby and picture. You must be really proud - congratulations! >> >> --Subutai >> >> >> On Fri, Jan 31, 2014 at 11:00 AM, Jeff Fohl <[email protected]> wrote: >> >>> Thanks! In that picture, I think he is contemplating how basic shapes of >>> light and shadow are being hierarchically organized in his memory in real >>> time to form invariant representations of the world around him. Or, maybe >>> he just pooped. Not sure which. >>> >>> >>> On Fri, Jan 31, 2014 at 10:37 AM, Matthew Taylor <[email protected]>wrote: >>> >>>> What a beautiful baby! Congrats! >>>> >>>> --------- >>>> Matt Taylor >>>> OS Community Flag-Bearer >>>> Numenta >>>> >>>> >>>> On Fri, Jan 31, 2014 at 10:36 AM, Jeff Fohl <[email protected]> wrote: >>>> >>>>> Thanks Fergal! Here is a picture of him a few hours old: >>>>> https://plus.google.com/+JeffFohl/posts/UKf4CvcNqQU >>>>> >>>>> >>>>> On Fri, Jan 31, 2014 at 10:34 AM, Fergal Byrne < >>>>> [email protected]> wrote: >>>>> >>>>>> Welcome to a lovely world Owen! Put that pic on the list, daddy! >>>>>> >>>>>> Regards >>>>>> Fergal >>>>>> -- >>>>>> Sent from Mailbox <https://www.dropbox.com/mailbox> for iPhone >>>>>> >>>>>> _______________________________________________ >>>>>> 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 >>>> >>>> >>> >>> _______________________________________________ >>> 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 >> >> > -------------- next part -------------- > An HTML attachment was scrubbed... > URL: > <http://lists.numenta.org/pipermail/nupic_lists.numenta.org/attachments/20140206/d4b9a120/attachment-0001.html> > > ------------------------------ > > Message: 5 > Date: Thu, 6 Feb 2014 19:20:35 -0800 > From: Erik Blas <[email protected]> > To: "NuPIC general mailing list." <[email protected]> > Subject: Re: [nupic-discuss] First commercial product built on NuPIC > Message-ID: > <CAHmtO-ykBgVNYdM7e3Ttn8Xu1L=mjeto_m+8kiiajuqjx3i...@mail.gmail.com> > Content-Type: text/plain; charset="iso-8859-1" > > Gratz on the release! > > > On Fri, Jan 31, 2014 at 9:35 AM, Jeff Fohl <[email protected]> wrote: > >> Terrific. Very nice to see! >> >> >> On Fri, Jan 31, 2014 at 9:15 AM, Matthew Taylor <[email protected]> wrote: >> >>> This is not a product pitch, but I thought you all might be interested to >>> know that the first commercial product built with NuPIC is live as an >>> Amazon Web Services application. We have a free version and a paid version. >>> >>> Free: https://aws.amazon.com/marketplace/pp/B00I18SNQ6 >>> Paid: https://aws.amazon.com/marketplace/pp/B00HJAA5MM >>> >>> This is Numenta's product that we've been building for the past year or >>> so, called Grok. It uses NuPIC's anomaly scores to give anomaly alerts to >>> IT folks for their AWS assets. It's a pretty cool usage of NuPIC, if I do >>> say so myself! And there are lots of opportunities for us to expand it's >>> functionality as NuPIC adds features. >>> >>> Over the next couple of years, I hope to see more commercial applications >>> take advantage of NuPIC's capabilities as it evolves. >>> >>> Regards, >>> --------- >>> Matt Taylor >>> OS Community Flag-Bearer >>> Numenta >>> >>> Disclaimer: I helped build this application before I switched over the >>> NuPIC full time. :P >>> >>> >>> _______________________________________________ >>> 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 >> >> > -------------- next part -------------- > An HTML attachment was scrubbed... > URL: > <http://lists.numenta.org/pipermail/nupic_lists.numenta.org/attachments/20140206/f04450ff/attachment-0001.html> > > ------------------------------ > > Message: 6 > Date: Thu, 6 Feb 2014 20:23:26 -0800 > From: Jeff Fohl <[email protected]> > To: "NuPIC general mailing list." <[email protected]> > Subject: Re: [nupic-discuss] Congrats Jeff > Message-ID: > <cadcvmcgzaeawmoatatbyuq7rywtenc7hayeqrohhmorqm59...@mail.gmail.com> > Content-Type: text/plain; charset="iso-8859-1" > > Thank you Erik! > > > On Thu, Feb 6, 2014 at 7:19 PM, Erik Blas <[email protected]> wrote: > >> Beautiful child! >> >> >> On Fri, Jan 31, 2014 at 1:04 PM, Subutai Ahmad <[email protected]>wrote: >> >>> Beautiful baby and picture. You must be really proud - congratulations! >>> >>> --Subutai >>> >>> >>> On Fri, Jan 31, 2014 at 11:00 AM, Jeff Fohl <[email protected]> wrote: >>> >>>> Thanks! In that picture, I think he is contemplating how basic shapes of >>>> light and shadow are being hierarchically organized in his memory in real >>>> time to form invariant representations of the world around him. Or, maybe >>>> he just pooped. Not sure which. >>>> >>>> >>>> On Fri, Jan 31, 2014 at 10:37 AM, Matthew Taylor <[email protected]>wrote: >>>> >>>>> What a beautiful baby! Congrats! >>>>> >>>>> --------- >>>>> Matt Taylor >>>>> OS Community Flag-Bearer >>>>> Numenta >>>>> >>>>> >>>>> On Fri, Jan 31, 2014 at 10:36 AM, Jeff Fohl <[email protected]> wrote: >>>>> >>>>>> Thanks Fergal! Here is a picture of him a few hours old: >>>>>> https://plus.google.com/+JeffFohl/posts/UKf4CvcNqQU >>>>>> >>>>>> >>>>>> On Fri, Jan 31, 2014 at 10:34 AM, Fergal Byrne < >>>>>> [email protected]> wrote: >>>>>> >>>>>>> Welcome to a lovely world Owen! Put that pic on the list, daddy! >>>>>>> >>>>>>> Regards >>>>>>> Fergal >>>>>>> -- >>>>>>> Sent from Mailbox <https://www.dropbox.com/mailbox> for iPhone >>>>>>> >>>>>>> _______________________________________________ >>>>>>> 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 >>>>> >>>>> >>>> >>>> _______________________________________________ >>>> 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 >> >> > -------------- next part -------------- > An HTML attachment was scrubbed... > URL: > <http://lists.numenta.org/pipermail/nupic_lists.numenta.org/attachments/20140206/51ecf42c/attachment-0001.html> > > ------------------------------ > > Message: 7 > Date: Fri, 7 Feb 2014 04:38:05 +0000 > From: Teri Fry <[email protected]> > To: NuPIC general mailing list. <[email protected]> > Subject: Re: [nupic-discuss] Congrats Jeff > Message-ID: > > <E90C5BFFA8755348A1D9242357E1753631D7016E@MBX021-W2-CA-2.exch021.domain.local> > > Content-Type: text/plain; charset="us-ascii" > > Jeff, > Congratulations! Owen looks like a deep thinker! He is beautiful. Enjoy! > Teri > > > From: nupic [mailto:[email protected]] On Behalf Of Jeff Fohl > Sent: Thursday, February 06, 2014 8:23 PM > To: NuPIC general mailing list. > Subject: Re: [nupic-discuss] Congrats Jeff > > Thank you Erik! > > On Thu, Feb 6, 2014 at 7:19 PM, Erik Blas > <[email protected]<mailto:[email protected]>> wrote: > Beautiful child! > > On Fri, Jan 31, 2014 at 1:04 PM, Subutai Ahmad > <[email protected]<mailto:[email protected]>> wrote: > Beautiful baby and picture. You must be really proud - congratulations! > > --Subutai > > On Fri, Jan 31, 2014 at 11:00 AM, Jeff Fohl > <[email protected]<mailto:[email protected]>> wrote: > Thanks! In that picture, I think he is contemplating how basic shapes of > light and shadow are being hierarchically organized in his memory in real > time to form invariant representations of the world around him. Or, maybe he > just pooped. Not sure which. > > On Fri, Jan 31, 2014 at 10:37 AM, Matthew Taylor > <[email protected]<mailto:[email protected]>> wrote: > What a beautiful baby! Congrats! > > --------- > Matt Taylor > OS Community Flag-Bearer > Numenta > > On Fri, Jan 31, 2014 at 10:36 AM, Jeff Fohl > <[email protected]<mailto:[email protected]>> wrote: > Thanks Fergal! Here is a picture of him a few hours old: > https://plus.google.com/+JeffFohl/posts/UKf4CvcNqQU > > On Fri, Jan 31, 2014 at 10:34 AM, Fergal Byrne > <[email protected]<mailto:[email protected]>> wrote: > Welcome to a lovely world Owen! Put that pic on the list, daddy! > > Regards > Fergal > - > Sent from Mailbox<https://www.dropbox.com/mailbox> for iPhone > > _______________________________________________ > nupic mailing list > [email protected]<mailto:[email protected]> > http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org > > > _______________________________________________ > nupic mailing list > [email protected]<mailto:[email protected]> > http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org > > > _______________________________________________ > nupic mailing list > [email protected]<mailto:[email protected]> > http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org > > > _______________________________________________ > nupic mailing list > [email protected]<mailto:[email protected]> > http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org > > > _______________________________________________ > nupic mailing list > [email protected]<mailto:[email protected]> > http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org > > > _______________________________________________ > nupic mailing list > [email protected]<mailto:[email protected]> > http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org > > -------------- next part -------------- > An HTML attachment was scrubbed... > URL: > <http://lists.numenta.org/pipermail/nupic_lists.numenta.org/attachments/20140207/66e93f3f/attachment.html> > > ------------------------------ > > Subject: Digest Footer > > _______________________________________________ > nupic mailing list > [email protected] > http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org > > > ------------------------------ > > End of nupic Digest, Vol 10, Issue 11 > ************************************* _______________________________________________ nupic mailing list [email protected] http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org
