Call For Participants -- NIPS*98 Workshop
SIMPLE INFERENCE HEURISTICS VS. COMPLEX DECISION MACHINES
Participants and presentations are invited for this post-NIPS workshop on the
contrast in both psychology and machine learning between a probabilistically-
defined view of rational decision making with its apparent demand for complex
Bayesian models, and a more performance-based view of rationality built on the
use of simple, fast and frugal decision heuristics.
Organizers:
Peter M. Todd (1), Laura Martignon (1), Kathryn Blackmond Laskey (2)
(1) Max Planck Institute for Human Development
Center for Adaptive Behavior and Cognition
Lentzeallee 94, 14195 Berlin GERMANY
ptodd@mpib-berlin.mpg.de, martignon@mpib-berlin.mpg.de
(2) Department of Systems Engineering
George Mason University
Fairfax, VA 22030-4444 USA
klaskey@gmu.edu
Background and aims of this workshop:
Ward Edwards has declared the 21st century to be the "Century of Bayes." The
identification of the rational ideal with the sort of probabilistic reasoning
that Bayes championed was first articulated during the Enlightenment, a time
of great enthusiasm for reason's potential to liberate humankind from the
shackles of dogma and superstition. This view of probabilistic rationality
gradually fell out of favor, so that by the beginning of this century
probability theory had become just another mathematical tool of the natural
sciences, used to model chance phenomena in the physical and social sciences
but no longer thought to be the calculus of enlightened human reason. But the
late 20th century has seen a resurgence of interest in probability as a model
for subjective degrees of belief. After initial skepticism, this view is
now flourishing in artificial intelligence and machine learning, and many
psychologists have returned to using probabilistic theories as normative
standards of rationality. Supporting this trend, the field of decision
analysis has focused on developing cognitive tools to help people become
better probabilists.
But at the same time, a number of psychologists and cognitive scientists have
come to reject the notion that logic and probability theory should be viewed
as normative ideals for human rationality. Instead, these researchers propose
that humans use simple evolved heuristics to draw domain-specific inferences
with incomplete knowledge, limited time, and bounded computational power.
Because these cognitive resources are constrained, human reasoning must rely
on a toolbox of "ecologically rational" fast and frugal decision-making
strategies adapted to the structure of information in the decision
environment. (See e.g. Gigerenzer, Todd, and the ABC Research Group, "Simple
heuristics that make us smart," Oxford University Press, in press.) In a
similar vein, many researchers in artificial intelligence and machine learning
argue that the most effective route to machine intelligence is to design more
or less simple, "boundedly rational" heuristic algorithms that make no attempt
at decision theoretic optimality.
This workshop brings together people in cognitive science, decision theory,
and machine learning to consider issues arising from the disagreement between
these two very different views of the nature of rationality. We will discuss
questions about the rationality and usefulness of simple vs. complex
decision-making strategies for humans and machines, including the following:
(1) What are the heuristics humans use for choice, categorization, estimation,
and comparison, and how do they relate to Bayesian approaches? (2) Are humans
approximate Bayesians in some sense? If so, how simple or complex are the
approximations involved? (3) How do the simple decision heuristics developed
in the machine learning community compare with the psychological and Bayesian
models? (4) Does decision theory play a useful role as a normative benchmark
for evaluating and comparing heuristic algorithms? If not, what standards
should be used instead? (5) In either case, what are the best strategies for
constructing "boundedly rational" algorithms that satisfy the traditional or
new standards of rationality?
We will structure the one-day workshop as two three-hour sessions, each
containing six short talks and a longer panel discussion involving all the
speakers and audience members. The morning session will concentrate on simple
and complex models of human decision-making, while the afternoon session will
focus on simple and complex machine learning models. In this way, we hope to
get those on both sides of the simplicity/complexity fence talking with each
other in each session.
If you are interested in participating in this workshop, either with a
presentation or just joining in the discussion, please contact one of the
organizers to help us schedule the presentations and discussions accordingly.
*****************************************************************************
µ