Hello,
Your idea of food interested me. I know a bit about food so I thought I'd
share some thoughts.

Trying this out would be pretty interesting. I think it would work. I'm
most excited by the prospect of creating new recipes using this.
I tried typing in various foods into the CEPT
demo<http://www.cept.at/demo_context_browser.html> [1]
and it matches foods reasonably well. So if you were to try generating new
recipes then I think you'd get some sensible food combinations.

However there might be a way of making this even better.
People have created large databases of
foods<http://flavorscience.net/blog/view/175/flavor_chemistry_databases_on_line>
[2],
listing the flavour compounds they contain. I've read about a chef who used
them to discover new food combinations. For example he found that caviar
and white chocolate go well
together<http://www.theguardian.com/lifeandstyle/2002/may/04/foodanddrink.shopping>because
they both contain a similar set of flavour compounds [3]. It might
be possible to somehow append these details onto a CEPT SDR.

Hopefully this information would lead to better food combinations. For
example apples and rose go well together because of their similarities in
flavour. However carrots and bananas don't go well together despite being
having similarities in shape.

Unfortunately most of these databases are behind big pay walls but I did
find a free (but less detailed) one
here<http://www.flavornet.org/flavornet.html> (see
the "Odors" tab) [4].


[1] - http://www.cept.at/demo_context_browser.html
[2] -
http://flavorscience.net/blog/view/175/flavor_chemistry_databases_on_line
[3] -
http://www.theguardian.com/lifeandstyle/2002/may/04/foodanddrink.shopping
[4] - http://www.flavornet.org/flavornet.html


Ruaridh


On Thu, Apr 10, 2014 at 6:17 AM, Chetan Surpur <[email protected]> wrote:

> Hi Matt,
>
> This indeed sounds like a great fit for NuPIC and CEPT. Check out Fluent
> (webapp [1], server-based API [2], Python library [3]), it was made for
> this!
>
> [1] http://fluent.cept.at/
> [2] https://github.com/numenta/nupic.fluent.server
> [3] https://github.com/numenta/nupic.fluent
>
> - Chetan
>
>
> On Wed, Apr 9, 2014 at 6:12 PM, Matt Roesener <[email protected]> wrote:
>
>> Hello everyone,
>>
>> While experimenting with the NLP projects using CEPT and the temporal
>> pooler, I came across an idea. Could I feed into the temporal pooler
>> ingredients data such as "tomato, onion..." or "eggs, bacon, potatoes",
>> learn the sequences, and make predictions of the next ingredient? My
>> thinking is to learn food associations from thousands of other food recipes
>> but also create new food associations or recipes?
>>
>> Is this this logic reasonable to accomplish using Nupic or will
>> additional regions be needed?
>>
>> Any thought process would be much appreciated!
>>
>> Thank you,
>>
>> Matt
>>
>>
>>
>> _______________________________________________
>> 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

Reply via email to