Abstract for AISB 2000: How to Design a Functioning Mind

Abstract for the
Symposium on How to Design a Functioning Mind
17-18th April 2000
At the AISB'00 Convention

AUTHOR: Stan Franklin, The University of Memphis

TITLE A "Consciousness" Based Architecture for a Functioning Mind


Here we describe an architecture designed to accommodate multiple
aspects of human mental functioning. In a roughly star-shaped
configuration centered on a "consciousness" module, the
architecture accommodates perception, associative memory,
emotions, action-selection, deliberation, language generation,
behavioral and perceptual learning, self-preservation and
metacognition modules. The various modules (partially) implement
several different theories of these various aspects of cognition.
The mechanisms used in implementing the several modules have been
inspired by a number of different "new AI" techniques. One
software agent embodying much of the architecture is in the
debugging stage (Bogner et al. in press). A second, intending to
include all of the modules of the architecture is well along in
the design stage (Franklin et al. 1998). The architecture,
together with the underlying mechanisms, comprises a fairly
comprehensive model of cognition (Franklin & Graesser 1999). The
most significant gap is the lack of such human-like senses as
vision and hearing, and the lack of real-world physical motor
output. The agents interact with their environments mostly
through email in natural language.

The "consciousness" module is based on global workspace theory
(Baars 1988, 1997). The central role of this module is due to its
ability to select relevant resources with which to deal with
incoming perceptions and with current internal states. Its
underlying mechanism was inspired by pandemonium theory (Jackson

The perception module employs analysis of surface features for
natural language understanding (Allen 1995).  It partially
implements perceptual symbol system theory (Barsalou 1999), while
its underlying mechanism constitutes a portion of the copycat
architecture (Hofstadter et al. 1994).

Within this architecture the emotions play something of the role
of the temperature in the copycat architecture and of the gain
control in pandemonium theory. They give quick indication of how
well things are going, and influence both action-selection and
memory. The theory behind this module was influenced by several
sources (Picard 1997, Johnson 1999, Rolls 1999). The
implementation is via pandemonium theory enhanced with an
activation-passing network.

The action-selection mechanism of this architecture is
implemented by a major enhancement of the behavior net (Maes
1990).  Behavior in this model corresponding to goal contexts in
global workspace theory. The net is fed at one end by
environmental and/or internal state influences, and at the other
by fundamental drives. Activation passes in both directions. The
behaviors compete for execution, that is, to become the dominant
goal context.

The deliberation and language generation modules are implemented
via pandemonium theory. The construction of scenarios and of
outgoing messages are both accomplished by repeated appeal to the
"consciousness" mechanism. Relevant events for the scenarios and
paragraphs for the messages offer themselves in response to
"conscious" broadcasts. The learning modules employ case-based
reasoning (Kolodner 1993) using information gleaned from human
correspondents. Metacognition is based on fuzzy classifier
systems (Valenzuela-Rendon 1991).

As in the copycat architecture, almost all of the actions taken
by the agents, both internal and external, are performed by
codelets. These are small pieces of code typically doing one
small job with little communication between them. Our
architecture can be thought of as a multi-agent system overlaid
with a few, more abstract mechanisms. Altogether, it offers one
possible architecture for a relatively fully functioning mind.
One could consider these agents as early attempts at the
exploration of design space and niche space (Sloman 1998).


Allen, J. J. 1995. Natural Language Understanding. Redwood City
CA: Benjamin/Cummings; Benjamin; Cummings.

Baars, B. J. 1988. A Cognitive Theory of Consciousness.
Cambridge: Cambridge University Press.

Baars, B. J. 1997. In the Theater of Consciousness. Oxford:
Oxford University Press.

Barsalou, L. W. 1999. Perceptual symbol systems. Behavioral and
Brain Sciences 22:577?609.

Bogner, M., U. Ramamurthy, and S. Franklin. in press.
Consciousness" and Conceptual Learning in a Socially Situated
Agent. In Human Cognition and Social Agent Technology, ed. K.
Dautenhahn. Amsterdam: John Benjamins.

Franklin, S., and A. Graesser. 1999. A Software Agent Model of
Consciousness. Consciousness and Cognition 8:285?305.

Franklin, S., A. Kelemen, and L. McCauley; 1998. IDA: A Cognitive
Agent Architecture. IEEE Conf on Systems, Man and Cybernetics.

Hofstadter, R. D., and  Mitchell M... 1994. The Copycat Project:
A model of mental fluidity and analogy-making. In: Advances in
connectionist and neural computation theory, Vol. 2: Analogical
connections, eds. K. J.

Holyoak & J. A. Barnden. Norwood N.J.: Ablex.

Jackson, J. V. 1987. Idea for a Mind. Siggart Newsletter,

Johnson, V. S. 1999. Why We Feel: The Science of Human Emotions.
Reading, MA: Perseus Books.

Kolodner, J. 1993. Case-Based Reasoning. : Morgan Kaufman.

Maes, P. 1990. How to do the right thing. Connection Science 1:3.

Picard, R. 1997. Affective Computing. Cambridge MA: The MIT

Rolls, E. T. 1999. The Brain and Emotion. Oxford: Oxford
University Press.

Sloman, A. 1998. The ``Semantics'' of Evolution: Trajectories and
Trade-offs in Design Space and Niche Space. In Progress in
Artificial Intelligence, ed. H. Coelho. Berlin: Springer.

Valenzuela-Rendon, M. 1991. The Fuzzy Classifier System: a
classifier System for Continuously Varying Variables. In:
Proceedings of the Fourth International Conference on Genetic
Algorithms. San Mateo CA: Morgan Kaufmann.

Some recent publications

"Is it an Agent, or just a Program?: A Taxonomy for Autonomous
Agents," (with A. C. Graesser),  Intelligent Agents III, Berlin:
Springer-Verlag, 1997, 21-35.

"Action Patterns, Conceptualization, and Artificial
Intelligence," Behavioral and Brain Sciences, 20 (1997) 23-24

"Autonomous Agents as Embodied AI", Cybernetics and Systems,
special issue on Epistemological Aspects of Embodied AI, 28:6
(1997) 499-520

"On Cooperation in Multi-Agent Systems," (with J. E. Doran, N.R.
Jennings and T.J. Norman), The Knowledge Engineering Review Vol
12 (3) 1997, 309-314.

"Global Workspace Agents," Journal of Consciousness Studies, 4
(4) 1997, 322-234.

"Learning Concepts in Software Agents," (with Uma Ramamurthy and
Aregahegn Negatu), in From Animals to Animat: Proceedings of the
Fifth International Conference of The Society for Adaptive
Behavior 98 (SAB98)

"Consciousness and Conceptual Learning in a Socially Situated
Agent," (with Myles Bogner and Uma Ramamurthy) in Kerstin
Dautenhahn ed. Human Cognition and Social Agent Technology, to

"A Software Agent Model of Consciousness," (with Art Graesser)
Consciousness and Cognition, 8, 1999, 285-301

Refereed conference publications

"Virtual Mattie -- an Intelligent Clerical Agent" (with Art
Graesser, Brent Olde, Hongjun Song, and Aregahegn Negatu),
presented to the AAAI Symposium on Embodied Cognition and Action,
Cambridge MA, November 1996.

"Natural Language Sensing for Autonomous Agents", (with Zhaohua
Zhang, Brent Olde, Art Graesser, and Yun Wan), IEEE INTERNATIONAL

"Simulating Smooth Tutorial Dialogue with Pedagogical Value,"
(with Arthur C. Grasser, Peter Wiemer-Hastings, and the Tutoring
Research Group), Proceedings of the 11th International FLAIRS
Conference, Menlo Park, CA: AAAI Press, 163-167

"Learning Concepts in Software Agents," (with Uma Ramamurthy  and
Aregahegn Negatu), in From animals to animats 5:  Proceedings of
The Fifth International Conference on Simulation of Adaptive
Behavior (ed. by Rolf Pfeifer, Bruce Blumberg, Jean-Arcady Meyer
and Stewart W. Wilson), August 1998, MIT Press, Cambridge,Mass.,
p 372-377

"Metacognition in Software Agents using Classifier Systems,"
(with Zhaohua Zhang and Dipankar Dasgupta), Fifteenth National
Conference on Artificial Intelligence, Madison, Wisconsin, 1998,

"IDA: A Cognitive Agent Architecture," (with Arpad Kelemen and
Lee McCauley), IEEE Conf on Systems, Man and Cybernetics, 1998,
to appear

"An Architecture for Emotions." (with Lee McCauley) In Papers
from the 1998 AAAI Fall Symposium entitled Emotional and
Intelligent: The Tangled Knot of Cognition, 122 - 127. AAAI
Press, Menlo. Park, CA.

"Evolutionary Economic Agents" (with Fergus Nolan, Jarek
Wilkiewicz, and Dipankar Dasgupta), AAAI to appear

"Behavioral Learning for Adaptive Software Agent" (with Aregahegn
Negatu), ISCA 8th International Conference on Intelligent
Systems, Denver, Colorado, June 24-26, 1999