Path: utzoo!attcan!uunet!samsung!sdd.hp.com!elroy.jpl.nasa.gov!usc!zaphod.mps.ohio-state.edu!ncar!boulder!ccncsu!handel.CS.ColoState.Edu!bogartc
From: bogartc@handel.CS.ColoState.Edu (Chris Bogart)
Newsgroups: comp.ai.neural-nets
Subject: Help with Quickprop
Message-ID: <7727@ccncsu.ColoState.EDU>
Date: 27 Jun 90 21:14:35 GMT
Sender: news@ccncsu.ColoState.EDU
Reply-To: bogartc@handel.UUCP (Chris Bogart)
Distribution: comp
Organization: Colorado State University, Fort Collins, CO  80523
Lines: 14


  I've been beating my head against the wall in frustration trying to
reproduce Fahlman's "quickprop" algorithm from his description of it
in:

  Fahlman, S.E. (1988) "Faster-Learning Variations on Back-Propagation:
An Empirical Study" in _Proceedings of the 1988 Connectionist Models
Summer School_, Morgan Kaufmann.

  Does anyone have or know of working quickprop code somewhere so I
can see what I'm doing wrong?

Thanks,
  Chris Bogart     bogartc@handel.cs.colostate.edu