home *** CD-ROM | disk | FTP | other *** search
/ NetNews Usenet Archive 1992 #18 / NN_1992_18.iso / spool / comp / ai / neuraln / 3204 < prev    next >
Encoding:
Text File  |  1992-08-16  |  960 b   |  25 lines
  1. Newsgroups: comp.ai.neural-nets
  2. Path: sparky!uunet!brunix!cs.brown.edu!pcm
  3. From: pcm@cs.brown.edu (Peter C. McCluskey)
  4. Subject: Re: Looking for a Recurrent Net algorithm
  5. Message-ID: <1992Aug16.140945.7949@cs.brown.edu>
  6. Sender: news@cs.brown.edu
  7. Organization: Brown Computer Science Dept.
  8. References:  <Aug13.194044.23182@yuma.ACNS.ColoState.EDU>
  9. Date: Sun, 16 Aug 1992 14:09:45 GMT
  10. Lines: 13
  11.  
  12. In article <Aug13.194044.23182@yuma.ACNS.ColoState.EDU>, ab509523@longs.LANCE.ColoState.Edu writes:
  13. |> 
  14. |>  I'me looking for a recurrent net algorithm as proposed by Pearlmutter.
  15.  
  16. See:
  17. Barak A. Pearlmutter, "Learning State Space Trajectories in Recurrent
  18. Neural Networks" in Neural Computation, vol 1, pp 263-269.
  19.  
  20. pearlmutter.dynets.ps.Z in the Neuroprose archives
  21. -- 
  22.          hardcore signature virus: "As a juror in a Trial by Jury, 
  23.          you have the right, power and duty to acquit the defendant 
  24.                  if you judge the law itself to be unjust."
  25.