Is a Learning Classifier System a Type of Neural Network?

This paper suggests a simple analogy between learning classifier systems (LCSs) and neural networks (NNs). By clarifying the relationship between LCSs and NNs, the paper indicates how techniques from one can be utilized in the other. The paper points out that the primary distinguishing characteristic of the LCS is its use of a co-adaptive genetic algorithm (GA), where the end product of evolution is a diverse population of individuals that cooperate to perform useful computation. This stands in contrast to typical GA/NN schemes, where a population of networks is employed to evolve a single, optimized network. To fully illustrate the LCS/NN analogy used in this paper, an LCS-like NN is implemented and tested. The test is constructed to run parallel to a similar GA/NN study that did not employ a co-adaptive GA. The test illustrates the LCS/NN analogy and suggests an interesting new method for applying GAs in NNs. Final comments discuss extensions of this work and suggest how LCS and NN studies can further benefit each other.

[1]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[2]  James S. Albus,et al.  I A New Approach to Manipulator Control: The I Cerebellar Model Articulation Controller , 1975 .

[3]  James S. Albus,et al.  New Approach to Manipulator Control: The Cerebellar Model Articulation Controller (CMAC)1 , 1975 .

[4]  John H. Holland,et al.  Cognitive systems based on adaptive algorithms , 1977, SGAR.

[5]  John H. Holland,et al.  COGNITIVE SYSTEMS BASED ON ADAPTIVE ALGORITHMS1 , 1978 .

[6]  Stephen F. Smith,et al.  A learning system based on genetic adaptive algorithms , 1980 .

[7]  S. Grossberg.  Studies of mind and brain : neural principles of learning, perception, development, cognition, and motor control , 1982 .

[8]  Lashon B. Booker,et al.  Intelligent Behavior as an Adaptation to the Task Environment , 1982 .

[9]  Alan S. Perelson,et al.  The immune system, adaptation, and machine learning , 1986 .

[10]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[11]  David E. Goldberg,et al.  Genetic Algorithms with Sharing for Multimodalfunction Optimization , 1987, ICGA.

[12]  James E. Baker,et al.  Reducing Bias and Inefficienry in the Selection Algorithm , 1987, ICGA.

[13]  John H. Holland,et al.  Induction: Processes of Inference, Learning, and Discovery , 1987, IEEE Expert.

[14]  Teuvo Kohonen,et al.  Self-Organization and Associative Memory , 1988 .

[15]  Lawrence Davis,et al.  Mapping Classifier Systems Into Neural Networks , 1988, NIPS.

[16]  Stephen Grossberg,et al.  The ART of adaptive pattern recognition by a self-organizing neural network , 1988, Computer.

[17]  Lawrence Davis,et al.  Mapping Neural Networks into Classifier Systems , 1989, ICGA.

[18]  Thomas P. Caudell,et al.  Parametric Connectivity: Training of Constrained Networks using Genetic Algorithms , 1989, ICGA.

[19]  Lashon B. Booker,et al.  Triggered Rule Discovery in Classifier Systems , 1989, ICGA.

[20]  Tariq Samad,et al.  Towards the Genetic Synthesisof Neural Networks , 1989, ICGA.

[21]  Richard K. Belew,et al.  Back Propagation for the Classifier System , 1989, International Conference on Genetic Algorithms.

[22]  Christian Lebiere,et al.  The Cascade-Correlation Learning Architecture , 1989, NIPS.

[23]  L. Darrell Whitley,et al.  Optimizing Neural Networks Using FasterMore Accurate Genetic Search , 1989, ICGA.

[24]  Manuel Valenzuela-Rendón.  Boolean Analysis of Classifier Sets , 1989, ICGA.

[25]  John J. Greffenstette,et al.  A System for Learning Control Strategies with Genetic Algorithms , 1989 .

[26]  John J. Grefenstette,et al.  A System for Learning Control Strategies with Genetic Algorithms , 1989, ICGA.

[27]  Peter M. Todd,et al.  Designing Neural Networks using Genetic Algorithms , 1989, ICGA.

[28]  Stewart W. Wilson.  Perceptron redux: emergence of structure , 1990 .

[29]  J. Doyne Farmer,et al.  A Rosetta stone for connectionism , 1990 .

[30]  Andrew G. Barto,et al.  Connectionist learning for control: an overview , 1990 .

[31]  L. Darrell Whitley,et al.  Genetic Reinforcement Learning with Multilayer Neural Networks , 1991, ICGA.

[32]  Richard S. Sutton,et al.  Reinforcement learning architectures for animats , 1991 .

[33]  H. Sakano,et al.  Detection of somatic DNA recombination in the transgenic mouse brain. , 1991, Science.

[34]  Robert Elliott Smith.  Default hierarchy formation and memory exploitation in learning classifier systems , 1991 .

[35]  Jan Torreele,et al.  Temporal Processing with Recurrent Networks: An Evolutionary Approach , 1991, ICGA.

[36]  J. D. Schaffer,et al.  Combinations of genetic algorithms and neural networks: a survey of the state of the art , 1992, [Proceedings] COGANN-92: International Workshop on Combinations of Genetic Algorithms and Neural Networks.

[37]  Charles Leave.  Neural Networks: Algorithms, Applications and Programming Techniques , 1992 .

[38]  D. L. Prados,et al.  Training multilayered neural networks by replacing the least fit hidden neurons , 1992, Proceedings IEEE Southeastcon '92.

[39]  Duc Truong Pham,et al.  Adaptive control of dynamic systems using neural networks , 1993, Proceedings of IEEE Systems Man and Cybernetics Conference - SMC.

[40]  Alan S. Perelson,et al.  Searching for Diverse, Cooperative Populations with Genetic Algorithms , 1993, Evolutionary Computation.

[41]  Alan S. Perelson,et al.  Using Genetic Algorithms to Explore Pattern Recognition in the Immune System , 1993, Evolutionary Computation.

[42]  Ben J. A. Kröse,et al.  Learning from delayed rewards , 1995, Robotics Auton. Syst..