[ExI] ANN question

Adrian Tymes atymes at gmail.com
Wed Mar 15 05:29:20 UTC 2017

Careful with the quoting.  You attributed to you my line, and vice
versa.  I've sorted it out here.

On Tue, Mar 14, 2017 at 6:46 AM, William Flynn Wallace
<foozler83 at gmail.com> wrote:
> On Mon, Mar 13, 2017 at 6:14 PM, Adrian Tymes <atymes at gmail.com> wrote:
>> 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.
> My understanding is that a neuron is always firing.  It has an idle speed
> and if inhibitory stimuli come in it slows down, and if excitatory it speeds
> up.

At any given instant, a neuron may either be firing or have a time
until next firing - but a firing is a (mostly) discrete event, with
one firing distinct from the next.

If it was not distinct - if it was "always firing" - then there would
be no such thing as "speed" of firing.  Rather than toggle on then off
at various rates, it would simply be always on.

More information about the extropy-chat mailing list