home *** CD-ROM | disk | FTP | other *** search
- Comments: Gated by NETNEWS@AUVM.AMERICAN.EDU
- Path: sparky!uunet!zaphod.mps.ohio-state.edu!uwm.edu!psuvax1!psuvm!auvm!UIUC.EDU!G-CZIKO
- Message-ID: <199301051602.AA19409@ux1.cso.uiuc.edu>
- Newsgroups: bit.listserv.csg-l
- Date: Tue, 5 Jan 1993 10:02:02 -0600
- Sender: "Control Systems Group Network (CSGnet)" <CSG-L@UIUCVMD.BITNET>
- Comments: Warning -- original Sender: tag was cziko@UX1.CSO.UIUC.EDU
- From: "Gary A. Cziko" <g-cziko@UIUC.EDU>
- Subject: Function between I and O?
- Lines: 51
-
- [from Gary Cziko 920105.1523 GMT]
-
- Greg Williams(>) (920103 - 2) interacting with Rick Marken (>>)
-
-
- >>But will this demo convince a psychologist who is busily doing research
- >>based on the assumption that o = f(i). NO WAY, JOSE. S/he can
- >>always describe the results VERBALLY -- invoking the shiboliths of
- >>scientific psychology --"stimulus generalization", "response
- >>generalization", etc -- and they can get back to work.
-
- >It looks as though they might contest PCTers' claims QUANTITATIVELY,
- >too. It all hinges on their claim that your i and o are straw variables.
-
- Greg, have you gotten the Koza book on _Genetic Programming_ yet?
-
- It seems to me that this would be a nice problem for symbolic regression
- (i.e., function identification) using genetic programming. You could
- include all kinds of functions that you think could possibly relate the
- output to the input and then let evolution do its stuff to find the magic
- combination. If there is anyway to express the output as a function of the
- input, it seems to me that genetic programming should be able to snuff it
- out. These functions could involve time lags as well.
-
- Indeed, it might be fun to send a set of tracking task input and output
- data to Koza as a challenge to see if he can find a relationship between
- them. It should be quite baffling to him if he cannot--unless of course he
- understands PCT. If anyone has a nice set of such data (up to 2000 pairs
- of data points) for a WELL-CONTROLLED tracking task, send it to me and I
- could send it to Koza (he includes his e-mail address in the book--the
- first time I've seen a book author do that).
-
- As a note to others, particularly programmers interested in PCT, I am quite
- impressed by John Koza's book (1992, MIT Press) and would very much like to
- get others' opinions on it. It seems to me that genetic programming could
- be very useful for PCT purposes, at the least for modelling reorganization.
-
- --Gary
-
- P.S. I would like to rename my "3 pencils & 4 rubber bands" demonstration
- the "3 pencils" demo (shorter), although Rick's "same "stimulus" different
- "response"" is more generally descriptive.
- ------------------------------------------------------------------
- Gary A. Cziko Telephone: 217.333.8527
- Educational Psychology FAX: 217.244.7620
- University of Illinois E-mail: g-cziko@uiuc.edu
- 1310 S. Sixth Street Radio: N9MJZ
- 210 Education Building
- Champaign, Illinois 61820-6990
- USA
- ------------------------------------------------------------------
-