Path: utzoo!attcan!uunet!husc6!bbn!inmet!ishmael!inmet!authorplaceholder
From: ryer@inmet.UUCP
Newsgroups: comp.ai.neural-nets
Subject: Re: Learning arbitrary transfer functio
Message-ID: <163400002@inmet>
Date: 21 Nov 88 14:20:00 GMT
References: <399@uvaee.ee.virginia.EDU>
Lines: 21
Nf-ID: #R:uvaee.ee.virginia.EDU:-39900:inmet:163400002:000:749
Nf-From: inmet.UUCP!ryer    Nov 21 09:20:00 1988



>    So, how do human's learn non linear functions ?
>  
>        : you learn that x^2, for instance, is X times X.
>  
>     And how about X times Y ? How do humans learn that ?
>  
>        : you memorize it, for single digits, and
>        : for more than a single digit, you multiply streams
>           of digits together in a carry routine.
>     joe@amos.ling.ucsd.edu

Although my knowledge of neural nets is limited, I won't buy what is
written above.  Most persons can, for example, throw a baseball more
or less at the target in spite of gravity.  This requires a non-linear
calculation.  This is not done via multiplication tables.  Sure it is
done by "experience", but so are neural network calculations.

Mike Ryer
Intermetrics, Inc.