How can an engineer learn from neuroscientists

junior1 at ibm.net[Bernie Arruza] junior1 at ibm.net[Bernie Arruza]
Tue Mar 4 22:17:32 EST 1997


In <5fe0c1$1p2 at vixen.cso.uiuc.edu>, kspencer at s.psych.uiuc.edu (Kevin Spencer) writes:
>1990s have been proclaimed the "Decade of the Brain" ...
Don't assume that I'm not very aware about where the field of ANNs is in as
far as university research and industry. It's 1997 and am not impressed. 
if I hear about another Artificial Neural Network to do stock market predictions
I will scream !. I'm just saying that "some" researches are interested in 
mathematical elegance (I think someone else said this and I agree) and instinct
without attempting to validate their finding (looking at nature, not necessarily imitating
nature). 

>The train is going to slow down?  Are you kidding?  The train has been
>speeding up since -- well, IMHO I'd say the 40s (when McCulloch & Pitts
>introduced a neural network model), and our understanding of the
>relationships between brain and mind are constantly evolving.  This
>is truly an exciting time to be working in this area.  If you want
>technical breakthroughs, since about 1980 we've had: magnetoencephalography
>(MEG), EEG/MEG source localization, positron emission tomography, magnetic
>resonance imaging (MRI) and functional MRI.  If you want to talk about
>modeling -- did you hear about the connectionist "revolution" that started
>in the mid-80s?  That's just a short and skewed very list of the exciting
>developments that have driven the field recently.  (No offense to people
>working with animal models, I'm not very familiar with those techniques.)
Exactly my point. Too many engineers working with ANNs are not familiar
with medical techniques to study the brain (and even worse, the results that
are obtained with those studies). I'm just saying that as a result, we are 
not advancing as fast as we should and even worse we are reaching computational
limits that keep us from modeling the non-trivial problems. 
I still think that if things don't change the train is going to slow down, but
 I respect your opinion.

>
>Kevin
>-----------------------------------------------------------
>Kevin Spencer
>Cognitive Psychophysiology Laboratory and Beckman Institute
>University of Illinois at Urbana-Champaign
>kspencer at p300.cpl.uiuc.edu
>-----------------------------------------------------------


___________________________________
Bernie Arruza.
Boca Raton, Fl USA
__________________________________
__The_way_of_the_warrior_is_the___
__resolute_acceptance_of_death.___
__________________________________
___________Miyamoto_Musashi_______
___________The_Book_of_Five_Rings_
__________________________________




More information about the Neur-sci mailing list