i'm imagining a live interaction toy that displays all predictions while text is being typed. color or size of displayed text can indicate prediction strength. but if a prediction (aka suggestion) is clicked, it changes the word and the predictions from that point are recomputed.
for example: if i type this| ---------------------------------------- i might think about how i'm *choosing* words less common results here so this would expand on the search engine live search widgets somehow. maybe it could be integrated with a search or recommendation engine for actual results. On Fri, Feb 28, 2014 at 7:40 PM, Chetan Surpur <[email protected]> wrote: > As per request (@Francisco and others), you can now paste text into the > input text field, and watch all the text get added to the model. > > This closes https://github.com/numenta/nupic.fluent.server/issues/3. > > > On Fri, Feb 28, 2014 at 4:09 PM, Chetan Surpur <[email protected]> wrote: > >> Thanks everyone! I'm excited to see what the community can build off of >> this :) >> >> >> On Fri, Feb 28, 2014 at 7:43 AM, Matthew Taylor <[email protected]> wrote: >> >>> I'm quite happy with the demo app Chetan has put together. I want to >>> emphasize that there's a great opportunity for the community to expand upon >>> it and create further demos within the nupic.fluent.server that uses the >>> API Chetan's provided (both the REST API on the server and the underlying >>> nupic.fluent API for python projects) to create more interesting things. We >>> have more ideas of things to create, and over time we'll be providing more >>> pages of demos using CEPT and NuPIC. Jeff thinks there is some potential >>> here to create interesting word games. >>> >>> --------- >>> Matt Taylor >>> OS Community Flag-Bearer >>> Numenta >>> >>> >>> On Fri, Feb 28, 2014 at 6:02 AM, Francisco Webber <[email protected]>wrote: >>> >>>> Hi Chetan, >>>> This is really great news! >>>> I think that this initiative will boost the participation of more >>>> application oriented community members. The natural language domain has a >>>> big advantage, namely that it is fairly easy to create test, training and >>>> experimentation collections of (text) data. Furthermore it is easier to >>>> interpret a result of an experiment as natural language can be intuitively >>>> understood. >>>> But also the "algorithmic" part of the community will profit from this >>>> new infrastructure, as it will become much easier to create a controlled >>>> experimental setup that allows to evaluate improvements of the algorithms >>>> (on both sides Numenta as well as CEPT). >>>> A third big advantage for the whole "CLA-movement" will be the >>>> increased visibility for the grand public, based on application demos built >>>> with the Numenta-CEPT hybrid. >>>> >>>> One of the first questions that pop up in my mind is: How much, in >>>> terms of quantity, will this patch of 16K columns be able to learn and >>>> remind? >>>> >>>> We also plan to instantiate a dedicated CEPT resource for the purpose. >>>> I will update you in the coming days on the progress. >>>> >>>> Again, thumbs-up for Chetan >>>> >>>> Cheers >>>> >>>> Francisco >>>> >>>> On 28.02.2014, at 06:08, Chetan Surpur <[email protected]> wrote: >>>> >>>> Hi everyone, >>>> >>>> I'm happy to introduce a project I've been working on this week. It's a >>>> platform for language prediction, using NuPIC together with CEPT [1]. The >>>> goal is to make it easy for anyone to build a language-based demo of NuPIC >>>> without having to know any of the internals of the CLA or CEPT. >>>> >>>> In fact, I have not one, but *two* little projects to open up to you. >>>> >>>> The first is nupic.fluent [2], a python library. It builds off of >>>> Subutai's and Matt's hackathon demos [3]. With it, you can create a model, >>>> feed it a word (also called a "term"), and get a prediction for the next >>>> one. It's very simple - and that's the point. >>>> >>>> The second is nupic.fluent.server [4], a server-based API and sample >>>> web app using nupic.fluent at its core. You can use it to build a web-based >>>> demo of language prediction with NuPIC, something we invited the community >>>> to participate in during the last office hour [5]. >>>> >>>> But wait, there's more! I've hosted the Fluent server on an EC2 >>>> instance, so you all can play with the Fluent web app right now. Enjoy: >>>> >>>> http://bit.ly/nupic-fluent >>>> >>>> Note that it's far from production-ready, and it may go down at any >>>> time. That link is just a little taste for now; I aim to host it in a more >>>> permanent place soon. >>>> >>>> Here is a screenshot of it in action: >>>> >>>> <image.png> >>>> >>>> Lastly, I invite everyone in the community to come hack on this with >>>> me; it's under the same license as NuPIC. And of course, feel free to use >>>> it in your demos (but be wary, it's still very early and the API might/will >>>> change). >>>> >>>> Thanks, >>>> Chetan >>>> >>>> [1] http://www.cept.at/ >>>> [2] https://github.com/numenta/nupic.fluent >>>> [3] http://numenta.org/blog/#demos >>>> [4] https://github.com/numenta/nupic.fluent.server >>>> [5] http://www.youtube.com/watch?v=67q75RnU58A&feature=share&t=37m16s >>>> _______________________________________________ >>>> 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
