cottrell@NPRDC.ARPA (Gary Cottrell) (10/22/86)
SEMINAR
Understanding Dogs and Dognition:
A New Foundation for Design
Garrison W. Cottrell
Department of Dog Science
Condominium Community College of Southern California
There is a crisis in Dog-Human relations, as has been
evidenced by recent attempts to make dogs more "user-friendly"
(see Programming the User-Friendly Dog, Cottrell 1985a). A new
approach has appeared (Whineandpoop and Flossy, 1986) that claims
that previous attempts at Dog-Human Interfaces have floundered on
a basic misunderstanding of the Dog. The problem has been that
we have approached the Dog as if he was one of us - and he
certainly is not. Their perusal of the philosophies of
Holedigger and Mateyourauntie has led them to a new
understanding: A West Coast Understanding. There is no Objective
Reality[1] that we form internal representations of, rather,
organisms are structurally coupled[2] to their environment, the
so-called "seamless web" theory of cognition. Thus the
inside/outside dichotomy that has plagued AI researchers and dogs
for years is a false one[3]. This has led them to a whole new
way of understanding how dogs should be programmed.
In the past we have assumed some internal representation in
the dog's head (see Modelling the Intentional Behavior of the
Dog, Cottrell 1984b). In this new view, the reason dogs are so
dense is not that they have impoverished internal
representations, but that they don't have internal
representations. Instead, the dog is structurally coupled to the
world - he moves about embedded in the ooze of the environment,
and naturally, it slows him down. Not only that, but it is the
wrong environment - the human one, leading to continual
breakdown[4]. Thus our problem is in forming a consensual domain
with another species. We have to place ourselves in their domain
to hear them - this is termed "listening in the backyard".
We feel that there is much to be gained from combining their
view with the connectionist approach[5]. The problem is
combining the intensional programming of evolution with
extensional programming by the owner. Connectionist theories of
learning combined with considerations of "listening in the
backyard" suggest that if we simply present the dog with many
examples of the desired input-output behavior within the
backyard, we will get the desired result.
____________________
[1]Actually, Californians have known this for years.
[2]Note that this is to be distinguished from the structural
coupling that produces new dogs from old ones.
[3]Dogs have often followed Mateyourauntie in this, ignoring
the inside/outside dichotomy. These considerations may eliminate
the basis for the continence-performance distinction (Hutchins,
1986).
[4]The field of Dog-Machine Interfaces attempts to deal with
such problems as the poor design of the doorknob - a lever would
help reduce the inside/outside barrier. Others feel that this
research is misdirected; the doorknob is designed that way pre-
cisely because it acts as a species filter, keeping dogs out of
restaurants and movie theatres.
[5]Their work also suggests applying the theory of speech acts
to the command interface. Thus, we can classify much more than
simple Directives. For example, "You've had it now, Jellybean!"
is a commissive - the speaker is committed to a future course of
action. The dog will usually respond with an attempt to withdraw
from the dialogue, but the speaker rejects his withdrawal.
"You're in the doghouse, Bean" is a declarative - the speaker
brings about a correspondence between the propositional content
of this and reality simply by uttering it.
P.S. As usual, troff source (1 page laser printer output) on request to:
gary cottrell
Institute for Cognitive Science, UCSD
cottrell@nprdc (ARPA)
{ucbvax,decvax,akgua,dcdwest}!sdcsvax!sdics!cottrell (USENET)