IUBio

Connectionist Learning - Some New Ideas

dog dog at cogsci.ed.ac.uk
Thu May 30 05:01:44 EST 1996


Jeff Baldwin wrote:
> ... to generalize such
> simplistic mathematical treatment to all purviews of simulated neural
> network applications and thereby also require all generalizations to
> adhere strictly to supposed biophysical rules misses the pragmatic mark.
> The simplest implementation of a simulated neural network system may only
> need to be _inspired_ by an observation of biophysical reality; it need
> not be a true emulation of bio-reality in order to be useful. Perhaps a
> name change will suffice to separate the wheat from the chaff? Perhaps
> "Simulated Pseudo-Neural Networks" or somesuch?

We already use the terms "ANN" (artificial neural network) and "BNN"
(biological neural network). Given that a sufficiently detailed artificial
model of any BNN is currently impossible, neologisms are unnecessary.

To anyone who wants to flame me for the term "sufficiently", I would say:
provide me with a model you believe to be sufficiently detailed and I will
show you a generalisation of extreme proportions.

dog
-- 
mailto:dog at cogsci.ed.ac.uk
http://www.cogsci.ed.ac.uk/~dog



More information about the Neur-sci mailing list

Send comments to us at biosci-help [At] net.bio.net