Newsgroups: comp.ai.neural-nets
Path: cantaloupe.srv.cs.cmu.edu!nntp.club.cc.cmu.edu!hudson.lm.com!news.pop.psu.edu!news.cac.psu.edu!howland.reston.ans.net!europa.eng.gtefsd.com!news.umbc.edu!haven.umd.edu!purdue!news.cs.indiana.edu!fcummins@cs.indiana.edu
From: "Fred Cummins" <fcummins@cs.indiana.edu>
Subject: Q: Periodic activation functions
Message-ID: <1994Nov4.180005.18032@news.cs.indiana.edu>
Sender: root@news.cs.indiana.edu (Operator)
Organization: Computer Science, Indiana University
Date: Fri, 4 Nov 1994 13:00:02 -0500
Lines: 19


Has anybody experience with or know of articles related to the use of
periodic activation functions (sinusoids etc) instead of the more
traditional motonically increasing functions (tanh, sigmoid...)?

Any pointers would be appreciated and I will post a summary if
critical mass is reached.

Fred

-- 
Fred Cummins		fcummins@cs.indiana.edu 
Lindley Hall 406,	(812) 855-8702 (office) 
Indiana University,	 (812) 339-7624 (home)  
Bloomington IN 47405
____________________________________________________________
Never give a monster the work of an eee-vill scientist......
------------------------------------------------------------         

