Thanks for the pointers everyone.  Very useful.

On Wed, Oct 21, 2015 at 1:19 PM, David Ray <[email protected]>
wrote:

> Hi Carin,
>
> To add to what Alex said, allegories for each of the Python end points
> exist for Java also. I'm on mobile right now because I'm getting Electrical
> work done; so it would be difficult to prepare a list of links, but I can
> as soon as I arrive at the coffee shop.
>
> You can get an example for the use of the Metrics Alex speaks of by
> looking at the Breaking News demo; together with an example of using a
> combination of the different end points. Additionally the fox eats demo
> shows you how to get a fingerprint out of the cortical API put it into the
> HTM and then get the results out of the HTM and do a reverse look up on the
> cortical API to get a human-readable term back.
>
> One more point the cortical API is good for disambiguation of contexts and
> it can also give you a similar list of terms used in multiple languages;
> you also can differentiate contacts by subtracting context from a term for
> instance:
> Apple - Jaguar would give you a context which eliminates the animal
> context and perhaps give you music or computers.
>
> Last but not least there's also an Android API
>
> Cheers,
> David
>
> Sent from my iPhone
>
> On Oct 21, 2015, at 11:55 AM, Alex Lavin <[email protected]> wrote:
>
> Hi Carin,
> I’ve run some experiments with the Cortical.io <http://cortical.io>
> classify endpoint and have found it to be a useful tool. The Python client
> allows you to query the endpoint [1] with positive examples that represent
> the class, and negative examples that do not; it may be useful to use the
> negative examples as those which may cause false positives. In return you
> get a fingerprint (bitmap) representing the class. Now you can classify
> text examples by first getting their fingerprints (via the term or text
> endpoints [2, 3]), and then calculating the distance to the category
> fingerprints; the API also offers an endpoint with many distance
> calculations [4]. So once you’ve created multiple category fingerprints you
> can classify text by determining which category is “closest”, as defined by
> the distance metrics.
>
> [1]
> https://github.com/cortical-io/python-client-sdk/blob/master/cortical/classifyApi.py
> [2]
> https://github.com/cortical-io/python-client-sdk/blob/master/cortical/termsApi.py
> [3]
> https://github.com/cortical-io/python-client-sdk/blob/master/cortical/textApi.py
> [4]
> https://github.com/cortical-io/python-client-sdk/blob/master/cortical/compareApi.py
>
> Cheers,
> Alex
>
>

Reply via email to