Newsgroups: comp.ai.neural-nets
Path: cantaloupe.srv.cs.cmu.edu!das-news2.harvard.edu!news2.near.net!howland.reston.ans.net!gatech!newsxfer.itd.umich.edu!gumby!wmu-coyote!borisov
From: borisov@cs.wmich.edu (Slava Borisov)
Subject: testing network with SNNS
Message-ID: <1995Mar11.185720.24658@sol.cs.wmich.edu>
Sender: news@sol.cs.wmich.edu (Usenet Maintenance)
Organization: Western Michigan Univ. Comp. Sci. Dept.
X-Newsreader: TIN [version 1.2 PL2]
Date: Sat, 11 Mar 1995 18:57:20 GMT
Lines: 17



Hi

I've got a problem with SNNS which should have a very simple
solution, I think.

Suppose I trained my network with 25 patterns. How how can I
see what will be produced if I feed a network with a pattern,
different from those 25 ? In other words, how can I test
the network's behavior on 'unseen' patterns ?

Thank you

Slava Borisov
borisov@cs.wmich.edu  

