home *** CD-ROM | disk | FTP | other *** search
- Path: sparky!uunet!darwin.sura.net!seismo!black
- From: black@seismo.CSS.GOV (Mike Black)
- Newsgroups: comp.ai.neural-nets
- Subject: Re: Neural Nets and Brains
- Message-ID: <50994@seismo.CSS.GOV>
- Date: 25 Jul 92 15:25:41 GMT
- References: <arms.711907358@spedden>> <BILL.92Jul23135614@ca3.nsma.arizona.edu> <arms.711935064@spedden>
- Sender: usenet@seismo.CSS.GOV
- Organization: Center for Seismic Studies, Arlington, VA
- Lines: 47
- Nntp-Posting-Host: beno.css.gov
-
- In article <arms.711935064@spedden> arms@cs.UAlberta.CA (Bill Armstrong) writes:
- >
- >The theory of multilayer perceptrons as used in BP is horrifying. You
- >need Kolmogorov's theorem just to show you can do everything you want
- >to approximate continuous functions, but nobody can apply it in
- >practice. In contrast, every logic designer who has heard of CNF and
- >DNF finds it *obvious* that a adaptive logic net can synthesize any
- >boolean function. So BP nets lose in a BIG way on the theory side, sorry.
- >
- I couldn't care less about theory...only results...
-
- >As for learning, BP is just gradient descent, and it leads to networks
- >that are *extremely* inefficient -- like trying to write C programs
- >with no conditional statements like "if" or "for" or "while". For
- >adaptive algorithms in logic networks that are far superior to
- >backprop, you can take a look at the atree release 2.6 adaptive logic
- >network simulator.
- >
- I will argue the superiority shortly...
-
- >Sorry, but after you have looked at ALN software, you may no longer
- >feel non-logical nets have any real advantages at all.
- >
-
- I took the atree software and (for times sake) reduced the multiplication
- problem to the 1 and 2 times tables. I removed 1*6 from the table and
- let atree crank. When I tested 1*6 it gave me an answer of ~35. I do
- NOT call this superior as the backprop net I trained gave me an answer
- that was at least BETWEEN 1*5 and 1*7. The other problem I ran into
- was running out of memory (16 meg + 64meg swap space) on a problem that
- I had previously solved with backprop.
-
- My conclusions:
-
- 1. backprop is able to generalize to a linear solution whereas atree
- cannot (in at least one provable case).
-
- 2. atree hits memory constraints before backprop does.
-
- 3. I have no doubt that atree does well in certain applications, but
- it NOT superior to backprop in ALL cases.
-
- --
- -------------------------------------------------------------------------------
- : usenet: black@beno.CSS.GOV : land line: 407-494-5853 : I want a computer:
- : real home: Melbourne, FL : home line: 407-242-8619 : that does it all!:
- -------------------------------------------------------------------------------
-