Deep Blue Cannot Play Checkers: The Need for Generalized Intelligence for Mobile Robots

Generalized intelligence is much more difficult than originally anticipated when Artificial Intelligence (AI) was first introduced in the early 1960s. Deep Blue, the chess playing supercomputer, was developed to defeat the top rated human chess player and successfully did so by defeating Gary Kasporov in 1997. However, Deep Blue only played chess; it did not play checkers, or any other games. Other examples of AI programs which learned and played games were successful at specific tasks, but generalizing the learned behavior to other domains was not attempted. So the question remains: Why is generalized intelligence so difficult? If complex tasks require a significant amount of development, time and task generalization is not easily accomplished, then a significant amount of effort is going to be required to develop an intelligent system. This approach will require a system of systems approach that uses many AI techniques: neural networks, fuzzy logic, and cognitive architectures.

[1]  Anthony V. Robins,et al.  A robust method for distinguishing between learned and spurious attractors , 2004, Neural Networks.

[2]  Rodney A. Brooks,et al.  Elephants don't play chess , 1990, Robotics Auton. Syst..

[3]  K. Holyoak,et al.  Surface and structural similarity in analogical transfer , 1987, Memory & cognition.

[4]  R. Schank.  The structure of episodes in memory , 1995 .

[5]  John A. Michon,et al.  Soar: A Cognitive Architecture in Perspective , 1992 .

[6]  K. A. Ericsson,et al.  The Influence of Experience and Deliberate Practice on the Development of Superior Expert Performance , 2006 .

[7]  James L. McClelland,et al.  On learning the past-tenses of English verbs: implicit rules or parallel distributed processing , 1986 .

[8]  K. Holyoak,et al.  Schema induction and analogical transfer , 1983, Cognitive Psychology.

[9]  James L. McClelland.  The Place of Modeling in Cognitive Science , 2009, Top. Cogn. Sci..

[10]  Lyle N. Long,et al.  Control of Mobile Robots Using the Soar Cognitive Architecture , 2009, J. Aerosp. Comput. Inf. Commun..

[11]  Ah Chung Tsoi,et al.  Lessons in Neural Network Training: Overfitting May be Harder than Expected , 1997, AAAI/IAAI.

[12]  Stephen Grossberg,et al.  Adaptive resonance theory: ART , 1998, An Introduction to Neural Networks.

[13]  Lyle N. Long,et al.  Hebbian learning with winner take all for spiking neural networks , 2009, 2009 International Joint Conference on Neural Networks.

[14]  Lyle N. Long,et al.  Review of Consciousness and the Possibility of Conscious Robots , 2010, J. Aerosp. Comput. Inf. Commun..

[15]  K. Holyoak,et al.  Analogical problem solving , 1980, Cognitive Psychology.

[16]  P Dean.  Recapitulation of a theme by Lashley? Comment on Wood's simulated lesion experiment. , 1980, Psychological review.

[17]  George A. Bekey,et al.  AUTONOMOUS ROBOTS, From Biological Inspiration to Implementation and Control, by G.A. Bekey, MIT Press, 2005, xv + 577 pp., index, ISBN 0-262-02578-7, 25 pages of references (Hb. £35.95) , 2005, Robotica.

[18]  Michael A. Arbib,et al.  The handbook of brain theory and neural networks , 1995, A Bradford book.

[19]  Michael McCloskey,et al.  Catastrophic Interference in Connectionist Networks: The Sequential Learning Problem , 1989 .

[20]  Troy D. Kelley,et al.  Symbolic and Sub-Symbolic Representations in Computational Models of Human Cognition , 2003 .

[21]  Todd Peterson,et al.  Hybrid learning incorporating neural and symbolic processes , 1998, 1998 IEEE International Conference on Fuzzy Systems Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36228).

[22]  Marvin Minsky,et al.  A framework for representing knowledge , 1974 .

[23]  D E Kieras,et al.  A computational theory of executive cognitive processes and multiple-task performance: Part 1. Basic mechanisms. , 1997, Psychological review.

[24]  Paul Thagard,et al.  Analogical Mapping by Constraint Satisfaction , 1989, Cogn. Sci..

[25]  John McCarthy,et al.  SOME PHILOSOPHICAL PROBLEMS FROM THE STANDPOINT OF ARTI CIAL INTELLIGENCE , 1987 .

[26]  L. R. Novick.  Analogical transfer, problem similarity, and expertise. , 1988, Journal of experimental psychology. Learning, memory, and cognition.

[27]  C. Lebiere,et al.  The Atomic Components of Thought , 1998 .

[28]  Sebastian Thrun,et al.  Lifelong Learning Algorithms , 1998, Learning to Learn.

[29]  L. Gottfredson.  Mainstream science on intelligence: An editorial with 52 signatories, history, and bibliography , 1997 .

[30]  Lyle N. Long,et al.  A hybrid symbolic and sub-symbolic intelligent system for mobile robots , 2009 .

[31]  Troy D. Kelley,et al.  Simulating Intelligent Behavior Requires a Complex Approach , 2006, AAAI Spring Symposium: Between a Rock and a Hard Place: Cognitive Science Principles Meet AI-Hard Problems.

[32]  Christopher J. Bishop,et al.  Pulsed Neural Networks , 1998 .

[33]  David Goodman,et al.  Man Versus Machine: Kasparov Versus Deep Blue , 1997, J. Int. Comput. Games Assoc..