Connectionists: Learning and Hidden Meanings

[Gabriele Scheler]

https://www.biorxiv.org/content/10.1101/658153v2

Maybe what one should be pointed out that there is no need for associative
learning in the model.
Also that the feature-based meanings of the 'concept neurons' are only
present when they are specifically activated. It is possible to compute
with concept neurons alone, making them have all the properties that
symbolic thought is good for - crisp instead of feature clouds, fast, and
abstract - no reference to their meaning unless needed.

Gabriele


--


Dr. Gabriele Scheler
Carl Correns Foundation for Mathematical Biology
1030 Judson Dr
Mountain View, CA 94040

https://www.theoretical-biology.org


Please re-send an email if I fail to respond.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/connectionists/attachments/20240617/cbdc43ef/attachment.html>