home *** CD-ROM | disk | FTP | other *** search
- Newsgroups: comp.ai.neural-nets
- Path: sparky!uunet!wupost!gumby!yale!cs.yale.edu!tsioutsias-dimitris
- From: tsioutsias-dimitris@CS.YALE.EDU (Dimitris Tsioutsias)
- Subject: ALN vs BP
- Message-ID: <1992Jul24.053623.22636@cs.yale.edu>
- Sender: news@cs.yale.edu (Usenet News)
- Nntp-Posting-Host: topaz.systemsx.cs.yale.edu
- Organization: Yale University Computer Science Dept., New Haven, CT 06520-2158
- Date: Fri, 24 Jul 1992 05:36:23 GMT
- Lines: 14
-
- It seems that after the backprop fans, we have now the ALN ones. Why
- each group (or any other that shows strong support) is trying to pass
- its nets as the dominant ones? It's like we should stop looking at
- anything else and concentrate all our efforts to the ALN's! Relax.
-
- The field of NN is still new and noone should draw any strong conclusions.
- We are still looking at different directions, trying various things,
- testing trends, dynamics, determining parameters, in a few words
- EXPERIMENTING. To claim that we have found the tool to work on
- and reject the rest, could be premature and wrong at this point.
-
- ->dimitris
- tsioutsias@cs.yale.edu
-
-