home *** CD-ROM | disk | FTP | other *** search
- Newsgroups: comp.ai.neural-nets
- Path: sparky!uunet!europa.asd.contel.com!darwin.sura.net!mojo.eng.umd.edu!disney.src.umd.edu!tedwards
- From: tedwards@src.umd.edu (Thomas Grant Edwards)
- Subject: Re: Thanks Neural Nets, and Brains?
- Message-ID: <1992Jul28.161114.22039@src.umd.edu>
- Sender: news@src.umd.edu (C-News)
- Organization: Systems Research Center, Maryversity of Uniland, College Park
- References: <arms.711907358@spedden> <1992Jul24.192734.26752@src.umd.edu> <675@trwacs.fp.trw.com>
- Date: Tue, 28 Jul 1992 16:11:14 GMT
- Lines: 22
-
- In article <675@trwacs.fp.trw.com> erwin@trwacs.fp.trw.com (Harry Erwin) writes:
- >>I also believe work on chaos in man-made neural nets may also be a
- >>useful tool for understanding chaos in real neural systems.
-
- >Why?
- >(What you're essentially saying is that the non-linearity of man-made
- >neural nets is similar to the non-linearity of real neural systems.)
-
- Work by Freeman (Neural Networks v.1 277-278) has shown chaotic
- activities in the
- rabbit olfactory system. Examination of this activity has indicated
- the use chaos as a novelty detector, and such dynamics have been
- modeled on a computer. Further work
- by Tsuda (Neural Networks, v. 5 pp 313-326) show the possibility of
- chaos as a dynamic link for memory and memory search. Of course,
- we await the electro-neurophysiology to determine whether Tsuda's
- model has any validity.
-
- -Thomas Edwards
-
-
-
-