home *** CD-ROM | disk | FTP | other *** search
- Newsgroups: comp.ai.neural-nets
- Path: sparky!uunet!spool.mu.edu!yale.edu!qt.cs.utexas.edu!cs.utexas.edu!torn!newshost.uwo.ca!gfx.engga.uwo.ca!krish
- From: krish@gfx.engga.uwo.ca (Mr. Venu Krishnapura)
- Subject: Need help with BP netsHi Everyone
- Organization: Univ. Western Ontario, London Ont. CA
- Date: Tue, 15 Dec 1992 15:36:30 GMT
- Message-ID: <1992Dec15.153630.15718@julian.uwo.ca>
- Sender: news@julian.uwo.ca (USENET News System)
- Nntp-Posting-Host: cad3.gfx.engga.uwo.ca
- Lines: 23
-
- Hi everyone:
- I seem to have messed up my earlier posting. I am reposting
- it here.
-
- I am trying to model a PRBS type data using BP nets.
- I am using a 2 layer network with the inner layer having a
- sigmoidal transfer function and the outer layer having a linear
- transfer function. My problem is that the network instead of
- following the PRBS data converges to the mean of the PRBS band
- width.
- My questions are:
- i) Am I justified in using the above transfer functions?
- If not, what should I be using?
- ii) Why is the network behaving so?
-
- I would appreciate your comments and suggestions. You
- may mail the same to my email address given below.
-
- Thanks
- venu
- -----------------------------------------------------------------
- Venugopal G. Krishnapura (519) 679 2111 Ext:8308
- Internet: krish@gfx.engga.uwo.ca
-