Genetic Matrix Algorithm; Simultaneous Optimization of Structure and Numerical Parameters
Wataru Fujishima, Tomoharu Nagao · IEEJ Transactions on Electrical and Electronic Engineering · 2007
Abstract Genetic Algorithm is often used to optimize numerical parameters, and Genetic Programming is used to optimize structure. However, optimizing both structure and numerical parameters simultaneously is quite difficult. Many different algorithms have been developed with the goal of optimizing both structure and numerical parameters simultaneously. However, those algorithms are not satisfactory in the sight of simultaneous optimization. We developed a new algorithm namedGenetic Matrix Algorithm(GMA), which can evolve structure and numerical parameters simultaneously. The new algorithm, GMA, can evolve tree‐structured programs, which include numerical parameters in each of the nonterminal nodes. In this paper, we apply GMA to evolve image processing algorithms. Experimental results show that we can construct new useful image processing algorithms, which cannot be constructed using only fixed thresholds. Copyright © 2007 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.