home *** CD-ROM | disk | FTP | other *** search
- Path: sparky!uunet!usc!elroy.jpl.nasa.gov!ames!network.ucsd.edu!sdcc12!cs!demers
- From: demers@cs.ucsd.edu (David DeMers)
- Newsgroups: comp.ai.neural-nets
- Subject: Re: Reducing Training time vs Generalisation
- Keywords: back propagation, training, generalisation
- Message-ID: <36944@sdcc12.ucsd.edu>
- Date: 18 Aug 92 04:08:56 GMT
- References: <arms.714014919@spedden> <36931@sdcc12.ucsd.edu> <arms.714091659@spedden>
- Sender: news@sdcc12.ucsd.edu
- Organization: =CSE Dept., U.C. San Diego
- Lines: 17
- Nntp-Posting-Host: beowulf.ucsd.edu
-
- In article <arms.714091659@spedden> arms@cs.UAlberta.CA (Bill Armstrong) writes:
- ...
-
- >PS I hope you don't take the "violins" comment too much to heart, but
- >the truth is that with a least squared error criterion on the training
- >set, I can get the optimal learned function to create a disaster very
- >easily.
-
- No offense, certainly. I guess I just don't understand what you
- mean by "disaster" nor what you've meant in previous postings
- about "wild" results...
-
- --
- Dave DeMers ddemers@UCSD demers@cs.ucsd.edu
- Computer Science & Engineering C-014 demers%cs@ucsd.bitnet
- UC San Diego ...!ucsd!cs!demers
- La Jolla, CA 92093-0114 (619) 534-0688, or -8187, FAX: (619) 534-7029
-