r norman <rsn_ at _comcast.net> writes:
> On 17 Dec 2003 15:55:57 -0500, Ashlie Benjamin Hocking
> <abh2n at cobra.cs.Virginia.EDU> wrote:
>> >SeeBelow at SeeBelow.Nut writes:
> >
> >> Do some readers of this newsgroup have an interest in Artificial Neural
> >> Networks?
> >>
> >> Mitchell Timin
> >>
> >> --
> >> "Many are stubborn in pursuit of the path they have chosen, few in
> >> pursuit of the goal." - Friedrich Nietzsche
> >>
> >> http://annevolve.sourceforge.net is what I'm into nowadays.
> >> Humans may write to me at this address: zenguy at shaw dot ca
> >
> >Some of us definitely do - but not all, I'm sure. I work with a
> >neuroscientist who has created a very successful neural network model
> >of the CA3 region of the hippocampus. (The model has also been
> >extended to other areas of the brain, but the CA3 region is definitely
> >the model's focus.)
> >
> There are two very different kinds of "artificial neural networks".
> One kind, like the modelling of the CA3 cells, is a computational
> technique to build models incorporating as much as possible about the
> known experimental details of real neurons -- the details being far
> too complex to understand without simulation. The other is to build
> networks of cells that only vaguely resemble true neurons but which
> can exhibit behavior reminiscent of what nervous systems do: learn,
> detect or generate patterns, .... These are two very distinct areas
> of work. And yes, there are certainly people here interested in each
> of these areas. Perhaps even some interested in both (and in
> neither). There are even those who claim that work in the second
> category is useful in understanding the first.
And at least one person (myself) who claims that work in the first
category is useful in understanding the second. Case in point:
D. W. Sullivan and W. B. Levy. Quantal synaptic failures improve
performance in a sequence learning model of hippocampal
CA3. Neurocomputing. 52-54 (2003) 397-401
I highly recommend this (short!) article to researchers in the second
category who don't think the first category has much to offer them! (I
know this was not implied by the previous poster, this is just an
uphill battle I find myself fighting - being a CS grad student who is
occasionally accused of studying neuroscience with little relevance to
CS.)
---------------------------------------------------------------------
| "Good and evil both increase at compound
Ben Hocking, Grad Student | interest. That is why the little
hocking at cs.virginia.edu | decisions you and I make every day are of
| such infinite importance." - C. S. Lewis
---------------------------------------------------------------------
