Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!swrinde!zaphod.mps.ohio-state.edu!rpi!sci.ccny.cuny.edu!phri!cmcl2!acf5!ambati
From: ambati@acf5.NYU.EDU (FJLevM{n[]Balamurali Ambati)
Newsgroups: comp.ai.neural-nets
Subject: Some Questions about NN
Message-ID: <1467@acf5.NYU.EDU>
Date: 31 Jan 91 17:16:40 GMT
Reply-To: ambati@acf5.UUCP (FJLevM{n[]Balamurali Ambati)
Organization: New York University
Lines: 21


Is it correct to say that people have had more success in modelling 
biological phenomena (i.e., in this case, describing neuronal networks 
in the visual pathway / hippocampus / ...) than in designing networks
to solve problems that the visual pathway / hippocampus / ... can 
solve?

A simple example is the immense difficulty in making a computer "see."
Of course, one of the problems is that "seeing" involves much more 
than the visual pathway alone.  But is this the only problem?

It's my understanding that Hopfield-Tank and other similar neural network 
models are not that useful (when compared to existing digital algorithms 
and even some genetic algorithms) in obtaining near-optimal solutions 
to combinatorial optimization problems such as TSP, etc.  Is this because
these models are simplistic in terms of describing the appropriate 
neurons?  Or is this because the human brain was not designed to solve 
TSP, etc.?  Is it worthwhile making neural networks that can themselves 
invent specific algorithms (somewhat like humans make machines solve 
specific problems)?  Is it possible / simple?

Balamurali K. Ambati