home *** CD-ROM | disk | FTP | other *** search
- Path: sparky!uunet!usc!rpi!uwm.edu!ogicse!das-news.harvard.edu!cantaloupe.srv.cs.cmu.edu!crabapple.srv.cs.cmu.edu!IUS4.IUS.CS.CMU.EDU!tjochem
- From: tjochem+@CS.CMU.EDU (Todd Jochem)
- Newsgroups: comp.ai.neural-nets
- Subject: Network Inversion
- Message-ID: <BtCqHo.AtH.1@cs.cmu.edu>
- Date: 21 Aug 92 21:03:23 GMT
- Article-I.D.: cs.BtCqHo.AtH.1
- Sender: news@cs.cmu.edu (Usenet News System)
- Organization: Carnegie Mellon University
- Lines: 14
- Nntp-Posting-Host: ius4.ius.cs.cmu.edu
-
- I'm looking for references to network inversion papers. The basic idea
- I'm interested in is presenting the network's output with a signal and
- by back-propagating this signal though the layer(s), recreating an input
- which could have created the applied output signal. I think that this could
- be pretty tough to do with some network configs. because of underdetermined
- linear equations, but would like pointers to any work that addresses this
- topic anyway. I'll summarize to the net any responses I get. Thanks,
-
- --Todd
-
- -------------------------------------------------------------------------------
- Todd Jochem The Robotics Institute (412) 268-3653
- Carnegie Mellon University
- tjochem@cs.cmu.edu Pittsburgh, PA 15213
-