home *** CD-ROM | disk | FTP | other *** search
- Newsgroups: comp.ai.fuzzy
- Path: sparky!uunet!zaphod.mps.ohio-state.edu!saimiri.primate.wisc.edu!ames!kronos.arc.nasa.gov!butch!netcomsv!netcom.com!gperkins
- From: gperkins@netcom.com (Glen C. Perkins)
- Subject: Re: WHEN and WHY should I use FUZZY logic?
- Message-ID: <1993Jan22.175728.5074@netcom.com>
- Organization: Netcom - Online Communication Services (408 241-9760 guest)
- References: <C15uAt.8nH@cpqhou.se.hou.compaq.com> <johnr.727592984@pongo.kowari.cpsg.com.au> <1993Jan21.174051.7469@netcom.com> <1jn5vmINNf44@shelley.u.washington.edu>
- Date: Fri, 22 Jan 1993 17:57:28 GMT
- Lines: 36
-
- chuckb@stein.u.washington.edu (Charles Bass) writes:
-
- >gperkins@netcom.com (Glen C. Perkins) writes:
-
- >>It's not always as easy as I make it sound, OBVIOUSLY, but
- >>tweaking these rules is almost always easier than deriving
- >>simultaneous differential equations in multiple variables
- >>from first principles!! And a control system based on these
-
- >If you don't know how to derive DE's from first principles this
- >is probably true. However, it is not *that* difficult, espcially
- >with symbolic math tools that have gained popularity over the
- >last few years.
-
- Easy for you... ;-) I asked the very same Bart Kosko that Erik
- was grumbling about a question approximately the same as yours:
- "why use fuzzy logic when we have [x and y and z methods]?" and
- his answer was (roughly): "because there are more problems
- than experts." If solving the problem of creating a controller
- that safely backs a car into a parking space can be done by a
- competent driver instead of requiring a specialist in non-linear
- control systems (or fill in your own example of a competent
- user versus an "expert") we'll get more problems solved. And
- there are quite a few problems where the first principles are
- so obscure (maybe even unknown) that having the ability to
- quickly build a model that reproduces observed behavior "well
- enough" comes in very handy. It doesn't follow, though, that
- fuzzy systems are always the best tools for a particular job.
- --
- +-----------------------+---------------------------------------------------+
- |--- Glen C. Perkins ---| |
- | <gperkins@netcom.com> | "Don't forget, your mind |
- | Native Guide Software | only *simulates* logic." |
- | Palo Alto, California | |
- +-----------------------+---------------------------------------------------+
-
-