Path: utzoo!utgpu!jarvis.csri.toronto.edu!mailrus!csd4.csd.uwm.edu!cs.utexas.edu!uunet!ncrlnk!ncr-sd!hp-sdd!ucsdhub!sdcsvax!beowulf!pluto
From: pluto@beowulf.ucsd.edu (Mark E. P. Plutowski)
Newsgroups: comp.ai.neural-nets
Subject: Re: : Step Function
Keywords: learning,generalization
Message-ID: <7011@sdcsvax.UCSD.Edu>
Date: 1 Sep 89 23:25:25 GMT
References: <1060@rex.cs.tulane.edu> <6980@sdcsvax.UCSD.Edu> <17538@bellcore.bellcore.com> <1727@cbnewsl.ATT.COM>
Sender: nobody@sdcsvax.UCSD.Edu
Reply-To: pluto@beowulf.UCSD.EDU (Mark E. P. Plutowski)
Organization: EE/CS Dept. U.C. San Diego
Lines: 13

In article <1727@cbnewsl.ATT.COM> apr@cbnewsl.ATT.COM (anthony.p.russo) 
writes:
>I can't tell you; this appears to be getting very deep. On the surface,
>it seems that biases are  !necessary! for learning anything at all.
>If so, then the biases are probably hard-wired and not learned, since
>they would have to be learned in terms of other biases, etc.
> ~ tony ~

Bias is indeed necessary to learn:  
if there is no bias, then there is no
criterion for selecting one hypothesis over another, and 
the learning algorithm can do no better than random selection,
on average.