home *** CD-ROM | disk | FTP | other *** search
/ NetNews Usenet Archive 1992 #19 / NN_1992_19.iso / spool / comp / ai / neuraln / 3337 < prev    next >
Encoding:
Text File  |  1992-08-27  |  836 b   |  18 lines
  1. Organization: Doctoral student, Psychology, Carnegie Mellon, Pittsburgh, PA
  2. Path: sparky!uunet!cis.ohio-state.edu!news.sei.cmu.edu!fs7.ece.cmu.edu!crabapple.srv.cs.cmu.edu!andrew.cmu.edu!qw0w+
  3. Newsgroups: comp.ai.neural-nets
  4. Message-ID: <UebQFB200iUy8821IO@andrew.cmu.edu>
  5. Date: Fri, 28 Aug 1992 02:14:37 -0400 
  6. From: Quanfeng Wu <qw0w+@andrew.cmu.edu>
  7. Subject: References on computational capacity of NN
  8. Lines: 8
  9.  
  10. Somewhere I read the notion the connectionist networks are
  11. computationally universal, i.e., computationally equivalent to the
  12. Turing machine. Is there any formal theoretical work proving or
  13. disproving this notion? I would appreciate references on theoretical
  14. work concerning computational, algorithmic, and/or informational
  15. capacities of various kinds of networks.
  16.  
  17. --Quanfeng Wu (Psychology, Carnegie Mellon University)
  18.