|This report is an introductory overview of learning by connectionist networks, also called arti cial neural networks, with a focus on the ideas and methods most relevant to the control of dynamical systems. It is intended both to provide an overview of connectionist ideas for control theorists and to provide connectionist researchers with an introduction to certain issues in control. The perspective taken emphasizes the continuity of the current connectionist research with more traditional research in control, signal processing, and pattern classi cation. Control theory is a well{developed eld with a large literature, and many of the learning methods being described by connectionists are closely related to methods that already have been intensively studied by adaptive control theorists. On the other hand, the directions that connectionists are taking these methods have characteristics that are absent in the traditional engineering approaches. This report describes these characteristics and discusses their positive and negative aspects. It is argued that connectionist approaches to control are special cases of memory{intensive approaches, provided a su ciently generalized view of memory is adopted. Because adaptive connectionist networks can cover the range between structureless lookup tables and highly constrained model{ based parameter estimation, they seem well{suited for the acquisition and storage of control information. Adaptive networks can strike a balance between the tradeo s associated with the extremes of the memory/model continuum. y The author acknowledges the support of the Air Force O ce of Scienti c Research, Bolling AFB, through grant AFOSR{87{0030, which made this chapter possible, and the support of the King's College Research Centre, King's College Cambridge, England, where much of it was written. Special appreciation is expressed to Chuck Anderson, Judy Franklin, Mike Jordan, Mitsuo Kawato, Rich Sutton, and Paul Werbos for useful discussions of the material presented in this chapter and many helpful suggestions on improving its presentation. This report is based on a talk given at the NSF Workshop on Neurocontrol, University of New Hampshire, October 1988. A version of this report will appear in Neural Networks for Control, T. Miller, R. S. Sutton, and P. J. Werbos (Eds.), The MIT Press, Cambridge, Massachusetts.
[1]
M. Aizerman,et al.
THEORETICAL BASES OF THE METHOD OF POTENTIAL FUNCTIONS IN THE PROBLEM ABOUT INSTRUCTION OF AUTOMATIC MACHINES ABOUT SEPARATION OF ENTRANCE SITUATIONS OF CLASSES
,
1964
.
[2]
J. Albus.
Mechanisms of planning and problem solving in the brain
,
1979
.
[3]
A G Barto,et al.
Learning by statistical cooperation of self-interested neuron-like computing elements.
,
1985,
Human neurobiology.
[4]
Charles W. Anderson,et al.
Learning and problem-solving with multilayer connectionist systems (adaptive, strategy learning, neural networks, reinforcement learning)
,
1986
.
[5]
Andrew G. Barto,et al.
Game-theoretic cooperativity in networks of self-interested units
,
1987
.
[6]
Charles W. Anderson,et al.
Strategy Learning with Multilayer Connectionist Representations
,
1987
.
[7]
Michael A. Arbib,et al.
Brains, machines and mathematics (2. ed.)
,
1987
.
[8]
Andrew G. Barto,et al.
From Chemotaxis to cooperativity: abstract exercises in neuronal learning strategies
,
1989
.
[9]
David J. Reinkensmeyer,et al.
Using associative content-addressable memories to control robots
,
1989,
Proceedings, 1989 International Conference on Robotics and Automation.
[10]
Andrew G. Barto,et al.
An approach to learning control surfaces by connectionist systems
,
1990
.