Genetic algorithms in noisy environments

Genetic algorithms are adaptive search techniques which have been used to learn high-performance knowledge structures in reactive environments that provide information in the form of payoff. In general, payoff can be viewed as a noisy function of the structure being evaluated, and the learning task can be viewed as an optimization problem in a noisy environment. Previous studies have shown that genetic algorithms can perform effectively in the presence of noise. This work explores in detail the tradeoffs between the amount of effort spent on evaluating each structure and the number of structures evaluated during a given iteration of the genetic algorithm. Theoretical analysis shows that, in some cases, more efficient search results from less accurate evaluations. Further evidence is provided by a case study in which genetic algorithms are used to obtain good registrations of digital images.

[1]  K. Dejong,et al.  An analysis of the behavior of a class of genetic adaptive systems , 1975 .

[2]  Lawrence Davis,et al.  Genetic Algorithms and Simulated Annealing , 1987 .

[3]  John J. Grefenstette,et al.  Technique For Automatic Motion Correction In Digital Subtraction Angiography , 1987 .

[4]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[5]  J. David Schaffer,et al.  Multi-Objective Learning via Genetic Algorithms , 1985, IJCAI.

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

[7]  Harvey F. Silverman,et al.  A Class of Algorithms for Fast Digital Image Registration , 1972, IEEE Transactions on Computers.

[8]  Lawrence J. Fogel,et al.  Artificial Intelligence through Simulated Evolution , 1966 .

[9]  Martin Svedlow,et al.  Image Registration: Similarity Measure and Preprocessing Method Comparisons , 1978, IEEE Transactions on Aerospace and Electronic Systems.

[10]  Alain Venot,et al.  Automated Correction of Patient Motion and Gray Values Prior to Subtraction in Digitized Angiography , 1984, IEEE Transactions on Medical Imaging.

[11]  John J. Grefenstette,et al.  Optimization of Control Parameters for Genetic Algorithms , 1986, IEEE Transactions on Systems, Man, and Cybernetics.

[12]  John J. Grefenstette,et al.  Genetic algorithms and their applications , 1987 .

[13]  John J. Grefenstette,et al.  Genetic Search with Approximate Function Evaluation , 1985, ICGA.

[14]  Iain D. Craig.  Genetic Algorithms and Simulated Annealing edited by Lawrence Davis Pitman, London, 1987 (£19.95) , 1988, Robotica.

[15]  John Merchant.  Exact Area Registration Of Different Views Of A Common Object Scene , 1981 .

[16]  Stewart W. Wilson.  Classifier systems and the animat problem , 2004, Machine Learning.

[17]  F. James,et al.  Monte Carlo theory and practice , 1980 .

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

[19]  Benny Lautrup,et al.  Monte Carlo methods in theoretical high-energy physics , 1985, CACM.

[20]  Stephen F. Smith,et al.  Flexible Learning of Problem Solving Heuristics Through Adaptive Search , 1983, IJCAI.

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

[22]  Ernest L. Hall,et al.  Computer Image Processing and Recognition , 1980, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[23]  Sam Kwong,et al.  Genetic algorithms and their applications , 1996, IEEE Signal Process. Mag..

[24]  Stewart W. Wilson.  Classifier Systems and the Animat Problem , 1987, Machine Learning.

[25]  John J. Grefenstette,et al.  Multilevel Credit Assignment in a Genetic Learning System , 1987, International Conference on Genetic Algorithms.

[26]  John Fitzpatrick,et al.  A class of one-to-one two-dimensional transformations , 1987 .