Modularity and Specialized Learning in the Organization of Behaviour

Research in artificial neural networks (ANN) has provided new insights for psychologists, particularly in the areas of memory, perception, representation and learning. However, the types and levels of psychological modelling possible in artificial neural systems is limited by the current state of the technology. This chapter discusses modularity as illuminated from research in complete agents, such as autonomous robots or virtual reality characters. We describe the sorts of modularity that have been found useful in agent research. We then consider the issues involved in modelling such systems neurally, particularly with respect to the implications of this work for learning and development. We conclude that such a syStem would be highly desirable, but currently poses serious technical challenges to the field of ANN. We propose that in the mean time, psychologists may want to consider modelling learning in specialised hybrid systems which can support both complex behaviour and neural learning.

[1]  J. Mink THE BASAL GANGLIA: FOCUSED SELECTION AND INHIBITION OF COMPETING MOTOR PROGRAMS , 1996, Progress in Neurobiology.

[2]  Julie A. Adams,et al.  Multiagent Systems: A Modern Approach to Distributed Artificial Intelligence , 2001, AI Mag..

[3]  Mark Mayfield,et al.  Object Models: Strategies, Patterns, and Applications , 1995 .

[4]  Joanna J. Bryson,et al.  Making Modularity Work: Combining Memory Systems and Intelligent Processes in a Dialog Agent , 2000 .

[5]  Phoebe Sengers,et al.  Antiboxology: agent design in cultural context , 1998 .

[6]  Robin R. Murphy,et al.  Artificial intelligence and mobile robots: case studies of successful robot systems , 1998 .

[7]  Amy L. Lansky,et al.  Reactive Reasoning and Planning , 1987, AAAI.

[8]  C. Gallistel The organization of learning , 1990 .

[9]  Gerhard Weiss,et al.  Multiagent systems: a modern approach to distributed artificial intelligence , 1999 .

[10]  Maja J. Mataric,et al.  Behaviour-based control: examples from navigation, learning, and group behaviour , 1997, J. Exp. Theor. Artif. Intell..

[11]  R. A. Brooks,et al.  Intelligence without Representation , 1991, Artif. Intell..

[12]  Erann Gat,et al.  Experiences with an architecture for intelligent, reactive agents , 1997, J. Exp. Theor. Artif. Intell..

[13]  Dietmar Heinke,et al.  Connectionist Models in Cognitive Neuroscience , 1999, Perspectives in Neural Computing.

[14]  David Hume Philosophical essays concerning human understanding , 1986 .

[15]  Erann Gat,et al.  Reliable goal-directed reactive control of autonomous mobile robots , 1991 .

[16]  Mark Mayfield,et al.  Object models (2nd ed.): strategies, patterns, and applications , 1997 .

[17]  James L. McClelland,et al.  Why there are complementary learning systems in the hippocampus and neocortex: insights from the successes and failures of connectionist models of learning and memory. , 1995, Psychological review.

[18]  M. Minsky The Society of Mind , 1986 .

[19]  Joanna Bryson,et al.  Cross-paradigm analysis of autonomous agent architecture , 2000, J. Exp. Theor. Artif. Intell..

[20]  G. Hall,et al.  The Interpretation of Dreams , 1914, Nature.

[21]  Rodney A. Brooks,et al.  Building brains for bodies , 1995, Auton. Robots.

[22]  N. Carlson Physiology of behavior , 1977 .

[23]  Lynn Andrea Stein,et al.  Challenging the Computational Metaphor: Implications for How We Think , 1999, Cybern. Syst..

[24]  Maja J. Matari,et al.  Behavior-based Control: Examples from Navigation, Learning, and Group Behavior , 1997 .

[25]  Stefan Schaal,et al.  Is imitation learning the route to humanoid robots? , 1999, Trends in Cognitive Sciences.

[26]  Robert M. French,et al.  Pseudopatterns and dual-network memory models: Advantages and shortcomings , 2000, NCPW.

[27]  John A. Bullinaria Exploring the Baldwin Effect in Evolving Adaptable Control Systems , 2000, NCPW.

[28]  Toby Tyrrell,et al.  Computational mechanisms for action selection , 1993 .

[29]  David C. Plaut,et al.  Systematicity and specialization in semantics , 1999 .

[30]  Ronald C. Arkin,et al.  An Behavior-based Robotics , 1998 .

[31]  Michael Wooldridge,et al.  Multiagent Systems: A Modern Approach to Distributed Artificial Intelligence , 1999 .