Path: utzoo!utgpu!news-server.csri.toronto.edu!mailrus!iuvax!rutgers!umn-d-ub!cs.umn.edu!msi-s6!mv10801 From: mv10801@msi-s6 (Jonathan Marshall [Learning Center]) Newsgroups: comp.ai.neural-nets Subject: Re: What good are neural nets? Summary: Generality, Locality Message-ID: <1990Mar23.020456.29253@cs.umn.edu> Date: 23 Mar 90 02:04:56 GMT References: <68764@aerospace.AERO.ORG> Sender: Jonathan A. Marshall Reply-To: mv10801@uc.msc.umn.edu (Jonathan Marshall [Learning Center]) Followup-To: comp.ai.neural-nets Organization: Center for Research in Learning, Perception, and Cognition Lines: 34 In article ted@nmsu.edu (Ted Dunning) writes: >i haven't yet found a single example where neural nets work better >(and i have looked). >can somebody come up with an example? The advantage of NNs is their generality. The point is not whether NNs outperform other approaches to specific problems. Rather, the main reason for using NNs is that the same basic mechanisms can work on a variety of problems. So what if a chess-playing AI program with 30-move lookahead could beat Bobby Fischer? The program wouldn't be good for much else. At least a human player can perform many other intelligent tasks. So what if certain statistical methods have better accuracy than NNs? When we find the correct NNs, they will be able to be used for many other tasks besides predicting loan defaults or learning XOR. Thus, your question about performance of NNs is both unfair and irrelevant. NNs ultimately will be designed for generality, not pure performance. Today's NNs, which are often applied to toy problems such as optimal graph traversal, loan approval, are primitive and are mainly useful only for research purposes. o o o o o o o o o o o o o o o o o o o o o o o o o o o o o o o o o o o o Jonathan A. Marshall mv10801@uc.msc.umn.edu o o Center for Research in Learning, Perception, and Cognition o o 205 Elliott Hall, University of Minnesota o o Minneapolis, MN 55455, U.S.A. o o o o o o o o o o o o o o o o o o o o o o o o o o o o o o o o o o o o