Title :
Are deception and complexity conjugate variables in genetic learning?
Author_Institution :
Comput. Resources Eng. Office, US Army Strategic Defense Command, Huntsville, AL, USA
Abstract :
This work provides an analytic starting point to the question: How deceptive is a randomly selected problem? It is shown that the bounding complexity of a large trap function is inversely proportional to the probability of a genetic algorithm encountering a fully deceptive instance, independent of problem size for gene length greater than 10 4. This result brings up interesting insights about the relationship between deception and complexity
Keywords :
computational complexity; genetic algorithms; learning (artificial intelligence); bounding complexity; complexity; conjugate variables; deception; genetic algorithm; genetic learning; large trap function; Cost function; Equations; Frequency; Genetic algorithms; Orbital robotics; Piecewise linear techniques; Testing;
Conference_Titel :
Evolutionary Computation, 1994. IEEE World Congress on Computational Intelligence., Proceedings of the First IEEE Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1899-4
DOI :
10.1109/ICEC.1994.349990
