[ExI] ANN question

Adrian Tymes atymes at gmail.com
Mon Mar 13 23:14:25 UTC 2017


On Mar 13, 2017 1:08 PM, "William Flynn Wallace" <foozler83 at gmail.com>
wrote:

Here's the relevant paragraph:

The Mcculloch Pitts neural model is an equation used to convert a series of
weighted inputs into a binary output.  Lots of data go in, and a 0 or a 1
comes out.  Add up a mess of numbers and if the solution is greater than or
equal to a predetermined total, the output is a 1.  If the solution falls
below the total, the output is a 0.  It's a simplified simulation of how
neurons in the brain work:  they either fire or don't fire.

OK, they did say 'simplified'.  But that's an incomplete picture of
neurons.  They can react to input in three ways, not just two:  not react
(meaning the firing rate stays the same), increase rate of firing, decrease
rate of firing.

Maybe the answer to my question is in that word 'simplified'.  Anybody?


I didn't see your actual question, but I see two points that might help:

The pattern of firing could change too, if that matters.  (Amplitude
doesn't change, right?  But might length of firing?  And is there
similarity between neurons changing their firing frequency, and frequency
modulation controls for radio transmission?)

The data could include how long since the neuron last fired   At any given
moment, a neuron is either firing or not, even if a given neuron's recent
firing history is critical data that simplified ANNs often ignore.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.extropy.org/pipermail/extropy-chat/attachments/20170313/403fe818/attachment.html>


More information about the extropy-chat mailing list