I'd think running asynchronously would be closer to modelling the biology
(not to mention making it easier to leverage multiple cores), but it would
also mean non-deterministic results in anything where the results of
computation were order-dependent.

-Tim

On Thu, Mar 5, 2015 at 4:27 PM, Fergal Byrne <[email protected]>
wrote:

> It's just an engineering simplification. In real neocortex, every neuron
> is racing against its own leakage currents, but you can get away with
> pretending that we have a timestep during which all the cells start from
> resting potential and simultaneously compete to fire.
>
> Using an actor model, you can do away with timesteps to that extent, but
> it's not as easy to visualise.
>
> Regards,
>
> Fergal Byrne
>
> On Thu, Mar 5, 2015 at 9:08 PM, Rich Morin <[email protected]> wrote:
>
>> On Mar 5, 2015, at 12:49, Fergal Byrne wrote:
>> > The region itself always just predicts one step ahead. ...
>>
>> The notion of a "step" seems to imply some sort of synchronous logic,
>> driven by a master clock.  Does the cortex actually work this way?
>>
>> Aside from curiosity, I'm asking because I've been thinking about the
>> problem of synchronizing the processing of an actor-based version of
>> NuPIC.  This seems like it would need to force all of the actors to
>> wait for the slowest actors, message paths, etc.
>>
>> So, I'm wondering about letting the actors operate asynchronoously,
>> handling and firing off messages as the scheduler (etc) allows.  Of
>> course, this would introduce some differences in the results, but
>> that might not be a problem.  Is this a reasonable approach to try?
>>
>> -r
>>
>>  --
>> http://www.cfcl.com/rdm           Rich Morin           [email protected]
>> http://www.cfcl.com/rdm/resume    San Bruno, CA, USA   +1 650-873-7841
>>
>> Software system design, development, and documentation
>>
>>
>>
>>
>
>
> --
>
> 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
>



-- 
http://timboudreau.com

Reply via email to