Path: utzoo!utgpu!jarvis.csri.toronto.edu!mailrus!csd4.csd.uwm.edu!cs.utexas.edu!uunet!mcsun!ukc!icdoc!flamingo.doc.ic.ac.uk!zmacv61
From: zmacv61@flamingo.doc.ic.ac.uk.doc.ic.ac.uk (L K C Leighton)
Newsgroups: comp.ai.neural-nets
Subject: Re: : Step Function
Message-ID: <1025@gould.doc.ic.ac.uk>
Date: 8 Sep 89 20:14:34 GMT
References: <1060@rex.cs.tulane.edu> <6980@sdcsvax.UCSD.Edu> <6981@sdcsvax.UCSD.Edu> <1667@cbnewsl.ATT.COM>
Sender: news@doc.ic.ac.uk
Reply-To: zmacv61@doc.ic.ac.uk (L K C Leighton)
Organization: Imperial College Department of Computing
Lines: 32


I am new to neural networks, and to news.  dubious as i was about sending
a message over the network, i had to query this:

>X-OR is *memorizable*, not learnable.

>In either case, learnability is not a requirement for neural net applicability.
>Nets memorize well.

i thought the whole idea of neural nets was to provide learning abilites, not
just to provide a memorising function.  computers these days are fast enough
as it is, and with good programming style, a good database can be provided
which would far outstrip any neural network.
        perhaps someone could enlighten me on this, as programs i have been
working on (limited to 1000 neurons approx) have centred around imitating the
brain.  i saw memory recall-type neural nets as limited, as they have no means
to link one neural pattern to another (thought processing we do all the time).
        also - does anyone have any programs along these lines, or any others.
as i am new to this subject, i have not yet tackled any books or articles on
this subject, and a lot of the terminology is lost on me.  programs i can
understand :-)

many thanks

	luke leighton.

| Luke Leighton @ Imperial College          |   zmacv61@uk.ac.ic.doc           |
| they said it was impossible.  i agreed.   |   tharg@uk.ac.ic.cc              |
| i said it was impossible. they disagreed. |   zdac131@uk.ac.kcl.cc.elm       |
| Luke Leighton @ Imperial College          |   zmacv61@uk.ac.ic.doc           |
| they said it was impossible.  i agreed.   |   tharg@uk.ac.ic.cc              |
| i said it was impossible. they disagreed. |   (On Janet :-)                  |