Naturally-Inspired Artificial Intelligence
AAAI 2008 Fall Symposium Series
November 7-9, Arlington, VA
The divide between how biological and computational systems solve
cognitive problems and adjust to novel circumstances is readily
apparent. While animals display marked flexibility in adjusting to
new situations, our current computational approaches excel in
well-defined, formally structured domains.
We are interested in new approaches to bridging this gap. Our
perspective is that studies of natural and artificial intelligences
can and should be mutually informative. Even young animals solve
historically difficult computational problems, and we believe
understanding how they do this will enable the creation of more
sophisticated artificial systems. Conversely, computational models
provide structure and insight into understanding animal learning and
cognition. By combining biological and computational perspectives, we
expect to obtain new insights that further the classical goals of
artificial intelligence.
This symposium is intended to bring together researchers working on
models that pertain directly to both natural and machine cognition.
Particular methodology, motivation, or implementation decisions do not
constrain our interests--we expect that relevant work may touch on
themes as diverse as human experiments, neural models, engineering of
complex systems, mathematical analysis, programming language design,
and high-level cognitive models, to name only a few possibilities. We
are interested in any work that has a clearly described relationship
between a line of investigation and the larger problem of producing
computational models that illuminate the peculiar nature and
capabilities of cognition.
Jacob Beal (BBN Technologies), Paul Bello (ONR)
Nick Cassimatis (RPI), Michael Coen (UW Madison), Patrick Winston (MIT)
- 9:00 am - 9:30 am: Introduction & Rules of Engagement (Patrick
Winston)
- 9:30 am - 10:40 am:
- ``Learning Hierarchical Representations and Behaviors''
(Robert A. Hearn, Richard H. Granger)
- ``Cognitive Mechanics: Natural Intelligence Beyond Biology and
Computation'' (Jon Doyle)
- ``Why Learning is Hard'' (Elizabeth Baraff Bonawitz, Laura
Schulz)
- 10:40 am - 11:00 am: Break
- 11:00 am - 11:50 am:
- ``How Tacit Knowledge Guides Action'' (Ya'akov Gal, Rajesh
Kasturirangen, Avi Pfeffer, Whitman Richards)
- ``Visual affordances and symmetries in Canis habilis: A
progress report'' (Thomas E. Horton, Lloyd Williams, Wei Mu,
Robert St. Amant)
- 11:50 am - 12:30 pm: Panel: Previous 5 presenters
- 12:30 pm - 2:00 pm: Lunch
- 2:00 pm - 3:30 pm:
- ``Men Are Dogs (and Women Too)'' (Ian Horswill)
- ``Toward a Process Model of Explanation with Implications for
the Type-Token Problem'' (John E. Hummel, David H. Landy, Derek
Devnich)
- ``Cognitive Development: Informing the Design of Architectures
for Natural Intelligence'' (Paul Bello)
- 3:30 pm - 4:00 pm: Break
- 4:00 pm - 4:50 pm:
- ``Probabilistic Strategy Selection for Flexible Cognition''
(Jennifer M. Roberts, Gregory Marton)
- ``Companion Cognitive Systems: Design Goals and Some Lessons
Learned'' (Ken Forbus, Matt Klenk, Tom Hinrichs)
- 4:50 pm - 5:30 pm: Panel: Previous 5 presenters
- 6:00 pm - 7:00 pm: Reception (All Symposia)
- 9:00 am - 9:25 am: ``Artificial Intelligence by Hook or by
Crook.'' (Michael Coen)
- 9:25 am - 10:45 am
- ``Collecting Semantics in the Wild: The StoryWorkbench'' (Mark
Alan Finlayson)
- ``Advice Taking and Transfer Learning: Naturally-Inspired
Extensions to Reinforcement Learning'' (Lisa Torrey, Trevor
Walker, Richard Maclin, Jude Shavlik)
- ``A Bayesian model of pedagogical reasoning'' (Patrick Shafto,
Noah Goodman)
- 10:45 am - 11:00 am Break
- 11:00 am - 11:50 am
- ``AI and Mental Imagery'' (Samuel Wintermute, Scott
D. Lathrop)
- ``Engineered Robustness by Controlled Hallucination'' (Jacob
Beal, Gerald Jay Sussman)
- 11:50 am - 12:30 pm Panel: Previous 5 presenters
- 12:30 pm - 2:00 pm Lunch
- 2:00 pm - 3:30 pm:
- ``Two Kinds of Paraphrase in Modeling Embodied Cognitive
Agents'' (Marjorie McShane, Sergei Nirenburg, Stephen Beale)
- ``A Naturalistic, Functional Approach to Modeling Language
Comprehension'' (Jerry T. Ball)
- ``Optimistic Problem Solving'' (Susan L. Epstein)
- 3:30 pm - 4:00 pm: Break
- 4:00 pm - 4:50 pm:
- ``Detecting the Evolution of Semantics and Individual Beliefs Through Statistical Analysis of Language Use'' (Avri Bilovich, Joanna Bryson)
- ``Modal Inference'' (Whitman Richards)
- 4:50 pm - 5:30 pm: Panel: Previous 5 presenters
- 5:45 pm - 7:15 pm: Plenary Session (All Symposia)
- 9:00 am - 10:30 am: Round-Table: Asking the Hard Questions
- 10:30 am - 11:00 am: Break
- 11:00 am - 12:30 pm: Round-Table: Where do we go from here?