From Optimization to Learning in Changing Environments: The Pittsburgh Immune Classifier System

A simple computational model of secondary immune response is used to provide a Pittsburgh style classiier system with the ability to improve its reaction to already encountered situations in a dynamical cyclic learning environment. Main results obtained with our core algorithm (YaSais) on Time Dependent Optimization problems are brieey reminded before to introduce the Pitts-burgh Immune Classiier System (PICS) which is then experimentally evaluated on both a static and dynamical multiplexer problem. Eventually, the Lazy Optimality EEect, keystone of YaSais' eeciency, is re-examinated in PICS. Suggested enhancements are then experimentally evaluated.

[1]  N. K. Jerne,et al.  Idiotypic Networks and Other Preconceived Ideas , 1984, Immunological reviews.

[2]  Ralf Salomon,et al.  Adaptation on the Evolutionary Time Scale: A Working Hypothesis and Basic Experiments , 1997, Artificial Evolution.

[3]  Kathleen M. Swigger,et al.  An Analysis of Genetic-Based Pattern Tracking and Cognitive-Based Component Tracking Models of Adaptation , 1983, AAAI.

[4]  Philippe Collard,et al.  Two models of immunization for time dependent optimization , 2000, Smc 2000 conference proceedings. 2000 ieee international conference on systems, man and cybernetics. 'cybernetics evolving to systems, humans, organizations, and their complex interactions' (cat. no.0.

[5]  Terence C. Fogarty,et al.  A Genetic Algorithm with Variable Range of Local Search for Tracking Changing Environments , 1996, PPSN.

[6]  Joseph Culberson,et al.  Genetic Invariance: A New Paradigm for Genetic Algorithm Design , 1992 .

[7]  Jerne Nk Towards a network theory of the immune system. , 1974 .

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

[9]  John J. Grefenstette,et al.  Genetic Algorithms for Tracking Changing Environments , 1993, ICGA.

[10]  Terence C. Fogarty,et al.  Comparison of steady state and generational genetic algorithms for use in nonstationary environments , 1996, Proceedings of IEEE International Conference on Evolutionary Computation.

[11]  John J. Grefenstette,et al.  Genetic Algorithms for Changing Environments , 1992, PPSN.

[12]  Alessio Gaspar,et al.  Secondary Immune Response for Evolutionary Time Dependent Optimization , 2002 .