HI Chetan,

Thanks for sharing that, it's a very good overview. Best viewed using the
link in the comments at
http://chris.ill-logic.com/systems-neuroscience/(the video is only
intermittently showing the slides).

Francisco and I had a great conversation at the hackathon about a possible
analogy between the CEPT SDR generation system and the ????? box shown
towards the end of the video. I have an idea that, by using a large corpus
of "textual memory", CEPTs retina is in a way reverse-engineering the
symbol-grounding mapping from word SDRs to high-level symbolic knowledge.
It is likely that representations of words and symbols in the brain are
indeed developed co-operatively by the regions "below" the word level
(speech, hearing, reading, writing) and, perhaps dominantly, by the act of
formation of concepts and memories connected with those words. CEPT is
striving to simulate the latter structure.

Regards,

Fergal Byrne





On Thu, Feb 6, 2014 at 3:28 AM, Chetan Surpur <[email protected]> wrote:

> In this talk, Demis Hassabis describes how the best approach to Artificial
> General Intelligence probably involves understanding and implementing the
> brain's algorithms. It affirms most of Numenta's values, and I found it to
> be an interesting listen. He even mentions the HTM briefly.
>
> Demis Hassabis: Combining systems neuroscience and machine learning: a new
> approach to AGI
> http://vimeo.com/m/17513841
>
> I was especially fascinated by his description of the neocortical /
> hippocampal system at the end. He says that the hippocampus implements
> short-term episodal memory, and replays these memories at high speed to the
> neocortex during sleep. It chooses memories to replay stochastically, while
> giving higher weighting to more emotionally salient memories. Thus it
> learns a more conceptual and relevant representation of the world rather
> than being limited by the statistics of the world's model. I wonder, how
> much of this is proven?
>
> He also talks about reinforcement learning, and how neurons that activate
> on dopamine release associated with the presence of a light cue learn to
> activate earlier, anticipating the light cue. It reminded me of the
> temporal pooling idea. I would love to learn more about details on what we
> know about how the brain implements reinforcement learning.
>
>
> _______________________________________________
> nupic mailing list
> [email protected]
> http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org
>
>


-- 

Fergal Byrne, Brenter IT

<http://www.examsupport.ie>http://inbits.com - Better Living through
Thoughtful Technology

e:[email protected] t:+353 83 4214179
Formerly of Adnet [email protected] http://www.adnet.ie
_______________________________________________
nupic mailing list
[email protected]
http://lists.numenta.org/mailman/listinfo/nupic_lists.numenta.org

Reply via email to