One of the big advantages of NLP is that evaluation can be done much easier and 
intuitively and that it is easy to get data for experiments. If we would 
provide functionalities that could create classifiers that based on 3 example 
sentences like this: "Albert Einstein is a physicist”, could then identify 
other (unseen) physicists. Or if we could have a system capable of boiling down 
a text of 5 pages into a meaningful abstract of one paragraph, anyone capable 
of reading and understanding english written text could evaluate the quality 
intuitively.
One important step in my opinion is to make experimentation much easier than it 
is right now.
Whoever wants to combine cortical.io and HTM apis needs a lot of knowledge and 
skills to do so. This is the reason why we currently put some effort in 
integrating our API into KNIME (www.knime.org). This is a scientific workflow  
development environment, similar to the more known “Rapidminer”, that allows 
easy implementation of experimental setups by non programers in a fraction of 
the time…
As soon as we have some minimal functionality on this platform, we will publish 
a first set of nodes including their source code. Then people who just want to 
experiment can download the free Knime-Desktop software and install the nodes. 
Others who want to extend the systems (cortical.io or nupic) can do this by 
adding new nodes themselves. There is a certain learning curve on how to 
implement Knime-nodes but as soon as you are into it it allows rapid 
implementation. And of course we will be happy to help and share our 
experiences with the community.
Hopefully I can show some results at the Hackathon…

All the Best

Francisco

On 29.09.2014, at 19:24, Fergal Byrne <[email protected]> wrote:

> Cheers, Subutai.
> 
> Vinh,
> 
> On NLP: cortical.io and NuPIC are already able to do some really interesting 
> things, but I believe this will really open up when we combine cortical.io on 
> real textual streams with the L4-L3 Temporal Pooling and hierarchy. 
> 
> On Video: the Deep Learning guys have made some pretty dramatic progress on 
> this recently - they seem to be using a type of multi-resolution rolled-out 
> hierarchy and a sort of saccading viewport.
> 
> This is a great example of how the slow brain deals with a million channels 
> of fast-changing input data streams. The neocortex learns which information 
> to throw away and still keep so much structure that it can do vision which 
> dedicated computer systems cannot match. It seems likely to me that we won't 
> require hardware to achieve similar feats with HTM; it can be done with a 
> software design built from the outset with parallelism and concurrency, and 
> aggressively exploiting sparsity (perhaps like the one I'm working on ;).
> 
> Regards,
> 
> Fergal Byrne
> 
> On Mon, Sep 29, 2014 at 5:18 PM, Subutai Ahmad <[email protected]> wrote:
> On Mon, Sep 29, 2014 at 6:31 AM, Fergal Byrne <[email protected]> 
> wrote:
> What they say, and perhaps it's worth thinking about, is that we would gain 
> credibility if we could demonstrate a "killer application" (what Ben Goertzel 
> calls the "AGI Sputnik moment") of HTM which shows it solving a problem 
> nobody else can even attempt to solve. For that, I believe, we'll need the 
> full sensorimotor stack and hierarchy, which we will have in the next few 
> months.
> 
> Could I ask people to have a think about this and possibly bounce around 
> ideas? We could schedule a round-table session during the hackathon next 
> month and see if there's an application area to focus on in this regard. The 
> most immediate candidates I can see right now are cortical.io (aka CEPT) for 
> NLP and the Geospatial Encoder.
> 
> Hi Fergal,
> 
> This is a really nice idea. I'm sure Jeff will be happy to participate as 
> well. Perhaps it is a discussion we can carry on during office hours as well.
> 
> --Subutai 
> 
> 
> 
> -- 
> 
> Fergal Byrne, Brenter IT
> 
> http://inbits.com - Better Living through Thoughtful Technology
> http://ie.linkedin.com/in/fergbyrne/ - https://github.com/fergalbyrne
> 
> Founder of Clortex: HTM in Clojure - 
> https://github.com/nupic-community/clortex
> 
> Author, Real Machine Intelligence with Clortex and NuPIC 
> Read for free or buy the book at https://leanpub.com/realsmartmachines
> 
> Speaking on Clortex and HTM/CLA at euroClojure Krakow, June 2014: 
> http://euroclojure.com/2014/
> and at LambdaJam Chicago, July 2014: http://www.lambdajam.com
> 
> e:[email protected] t:+353 83 4214179
> Join the quest for Machine Intelligence at http://numenta.org
> Formerly of Adnet [email protected] http://www.adnet.ie

Reply via email to