Return to The Humor Index.
InterWeavers.
==================================================================== FROM: CONNECTION SCIENCE: Journal of Neural Computing, Artificial Intelligence and Cognitive Research, Vol. 2, No. 3, 1990. ==================================================================== HUMOUR Understanding Dogs and Dognition: a New Foundation for Design. GARRISON W. COTTRELL There is a crisis in dog-human relations, as has been evidenced by recent attempts to make dogs more 'user-friendly' (see 'Programming the use-friendly dog', Cottrell, 1985). A new approach has appeared (Whineandpoop & 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 & 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 dognitive ;; scientists 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 'A hybrid model of the intentional behavior of the dog, Cottrell, 1989). 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 3 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 intentional programming of I' 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. Notes 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 precisely 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 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. Garrison W. Cottrell, Department of Dog Science, Condominium Community College of Southern California. Copyright Garrison Cottrell 1990.
SEMINAR
New approaches to learning in Connectionist Networks
Garrison W. Cottrell
Richard K. Belew
Institute for Neural Declamation
Condominium Community College of Southern California
Previous approaches to learning in recurrent networks often
involve batch learning: A large amount of effort is expended in
deciding which way to move in weight space, then a little step is
taken. We propose a new algorithm for learning in large networks
which is orders of magnitude more efficient than batch learning.
Based on the realization that many nearby points in weight space
are worse than where we are now, we propose the sanguine
algorithm. The basic idea is to become more happy with where we
are, rather than going to all the work of moving. Hence the
approach is quite simple: Randomly sample a nearby point in
weight space. Compute the error functional based on that point.
If it is better than the current point, repeat until we find a
nearby point that is worse. Now, here's the real trick: Once we
find a point worse off than where we are now, we stay where we
are and increment a "happiness function". That is, we search
until we find a place that we can "look down on" in weight
space[1].
Now, in order to remain happy with where we are may involve
a certain amount of minor work to keep this point in weight space
looking good. For example, we could change the error functional
until this point looks better than most other points we find.
Towards this end, we can apply recent techniques (Nowlan &
Hinton, 1991) to make the error functional soft and flabby. Then
we can stretch the error any way we like. This approach can also
be extended to replace computationally expensive "weight-sharing"
techniques. If we make the weights soft and flabby, then lifting
them becomes much easier since part of the weight always remains
on the ground, and sharing the burden of large weights becomes
unnecessary. Note that this can be done completely locally.
We have applied this novel learning procedure to the problem
of time series prediction. Using the Mackey-Glass equations with
dimension 3.5, we give the network values at 0, 6, 12, and 18
time units back in time to predict the value of the time series 6
time units into the future. Using the Sanguine Algorithm, a
network with only two hidden units rapidly converges to a soft
error functional. Of course, the network has no idea of what
value will come next; however, the happiness function shows it is
quite blissful in its ignorance. We propose that this technique
will have wide application in Republican approaches to
government.
____________________
[1]Thus the pet name for our algorithm is the "Nyah Nyah Algo-
rithm".
Copyright Garrison Cottrell 1990.
SEMINAR
Approaches to the Inverse Dogmatics Problem:
Time for a return to localist networks?
Garrison W. Cottrell
Department of Dog Science
Condominium Community College of Southern California
The innovative use of neural networks in the field of Dognitive
Science has spurred the intense interest of the philosophers of
Dognitive Science, the Dogmatists. The field of Dogmatics is devoted to
making sense of the effect of neural networks on the conceptual
underpinnings of Dognitive Science. Unfortunately, this flurry of
effort has caused researchers in the rest of the fields of Dognitive
Science to spend an inordinate amount of time attempting to make sense
of the philosophers, otherwise known as the Inverse Dogmatics problem
(Jordan, 1990). The problem seems to be that the philosophers have
allowed themselves an excess of degrees of freedom in conceptual space,
as it were, leaving the rest of us with an underconstrained optimization
problem: Should we bother listening to these folks, who may be somewhat
more interesting than old Star Trek reruns, or should we try and get our
work done?
The inverse dogmatics problem has become so prevalent that many
philosophers are having to explain themselves daily, much to the dismay
of the rest of the field. For example Gonad[1] (1990a, 1990b, 1990c,
1990d, 1990e, well, you get the idea...) has repeatedly stated that no
connectionist network can pass his usually Fatal Furring Fest, where the
model is picked apart, hair by hair[2], until the researchers making
counterarguments have long since died[3]. One approach to this problem
is to generate a connectionist network that is so hairy (e.g., Pollack's
RAMS, 1990), that it will outlast Gonad's attempt to pick it apart.
This is done by making a model that is at the sub-fur level, that
recursively splits hairs, RAMming more and more into each hair, which
generates a fractal representation that is not susceptible to linear
hair splitting arguments.
Another approach is to take Gonad head-on, and try to answer his
fundamental question, that is, the problem of how external discrete
nuggets get mapped into internal mush. This is known as the *grinding
problem*. In our approach to the grinding problem, we extend our
previous work on the Dog Tomatogastric Ganglion (TGG). The TGG is an
oscillating circuit in the dog's motor cortex that controls muscles in
the dog's stomach that expel tomatoes and other non-dogfood items from
the dog's stomach. In our grinding network, we will have a similar set
up, using recurrent bark propagation to train the network to oscillate
in such a way that muscles in the dog's mouth will grind the nuggets
____________________
[1]Some suspect that Gonad may in fact be an agent of reactionary
forces whose mission is to destroy Dognitive Science by filibuster.
[2]Thus by a simple morphophonological process of reduplication, ex-
haustive arguments have been replaced by exhausting arguments.
[3]In this respect, Gonad's approach resembles that of Pinky and
Prince, whose exhausting treatment of the Past Fence Model, Rumblephart
and McNugget's connectionist model of dog escapism, has generated a sub-
field of Dognitive Science composed of people trying to answer their ar-
guments.
into the appropriate internal representation. This representation is
completely distributed. This is then transferred directly into the
dog's head, or Mush Room. Thus the thinking done by this
representation, like most modern distributed representations, is not
Bayesian, but Hazyian.
If Gonad is not satisfied by this model, we have an alternative
approach to this problem. We have come up with a connectionist model
that has a *finite* number of things that can be said about it. In order
to do this we had to revert to a localist model, suggesting there may be
some use for them after all. We will propose that all connectionist
researchers boycott distributed models until the wave of interest by the
philosophers passes. Then we may get back to doing science. Thus we
must bring out some strong arguments in favor of localist models. The
first is that they are much more biologically plausible than distributed
models, since *just like real neurons*, the units themselves are much
more complicated than those used in simple PDP nets. Second, just like
the neuroscientists do with horseradish peroxidase, we can label the units
in our network, a major advantage being that we have many more labels
than the neuroscientists have, so we can keep ahead of them. Third, we
don't have to learn any more than we did in AI 101, because we can use
all of the same representations.
As an example of the kind of model we think researchers should turn
their attention to, we are proposing the logical successor to Anderson &
Bower's HAM model, SPAM, for SPreading Activation Memory model. In this
model, nodes represent language of thought propositions. Because we are
doing Dog Modeling, we can restrict ourselves to at most 5 primitive
ACTS: eat, sleep, fight, play, make whoopee. The dog's sequence of
daily activities can then be simply modeled by connectivity that
sequences through these units, with habituation causing sequence
transitions. A fundamental problem here is, if the dog's brain can be
modeled by 5 units, *what is the rest of the dog's brain doing?* Some
have posited that localist networks need multiple copies of every neuron
for reliability purposes, since if the make whoopee unit was
traumatized, the dog would no longer be able to make whoopee. Thus
these researchers would posit that the rest of the dog's brain is simply
made up of copies of these five neurons. However, we believe we have a
more esthetically pleasing solution to this problem that simultaneously
solves the size mismatch problem. The problem is that distributed
connectionists, when discussing the reliability problem of localist
networks, have in mind the wimpy little neurons that distributed models
use. We predict that Dognitive neuroscientists, when they actually
look, will find only five neurons in the dog's brain - but they will be
*really big* neurons.
Copyright Garrison Cottrell 1990.