home *** CD-ROM | disk | FTP | other *** search
/ NetNews Usenet Archive 1992 #20 / NN_1992_20.iso / spool / comp / ai / neuraln / 3481 < prev    next >
Encoding:
Text File  |  1992-09-14  |  745 b   |  20 lines
  1. Newsgroups: comp.ai.neural-nets
  2. Path: sparky!uunet!emba-news.uvm.edu!trantor.emba.uvm.edu!thibault
  3. From: thibault@trantor.emba.uvm.edu (Scott A Thibault)
  4. Subject: Evenly distributed categories for competetive learning?
  5. Message-ID: <1992Sep14.172002.8888@uvm.edu>
  6. Sender: news@uvm.edu
  7. Organization: University of Vermont, EMBA Computer Facility
  8. Date: Mon, 14 Sep 1992 17:20:02 GMT
  9. Lines: 9
  10.  
  11.  
  12.   I have a set of vectors that I'm categorizing using a competetive learning
  13. neural net.  I'd like to have at least one vector in each category and have
  14. them roughly evenly distirbuted.  Each output in the network represents a
  15. category.  As anyone done something like this or have any ideas?
  16.  
  17. --Scott Thibault
  18. University of Vermont
  19. thibault@emba.uvm.edu
  20.