[ExI] new neuron learning theory

Darin Sunley dsunley at gmail.com
Fri Apr 29 18:50:23 UTC 2022

Perceptron-style "neurons" were a simplified caricature of how neurologists
thought neurons /might/ work back in the 70s, even when they were first

Time and neurological research hasn't been kind to the comparison.

At this point, the only similarity between the basic elements of
network-based machine learning algorithms and mammalian brain cells is the
name. ML "neurons" are basically pure mathematical abstractions, completely
unmoored from anything biological cells actually do.

On Fri, Apr 29, 2022 at 12:01 PM William Flynn Wallace via extropy-chat <
extropy-chat at lists.extropy.org> wrote:

> https://neurosciencenews.com/dendrite-learning-20492/
> 'This changes everything' is trite, but maybe true here.   Notice that AIs
> are programmed according to the old theory of strengthened synapses.  Maybe
> that will change.  bill w
> _______________________________________________
> extropy-chat mailing list
> extropy-chat at lists.extropy.org
> http://lists.extropy.org/mailman/listinfo.cgi/extropy-chat
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.extropy.org/pipermail/extropy-chat/attachments/20220429/05e09a95/attachment.htm>

More information about the extropy-chat mailing list