控制理论与应用2001，Vol.18Issue(2)：281-284,4.
常见遗传多层前馈神经网络实数编码的不合理性分析和改进*
An Analysis and Improvement of the Shortcomings of the Common Real Number Coding Scheme in Genetic Multilayer Feedforward Neural Networks
摘要
Abstract
This paper theoretically analyses the problems in the common real number coding scheme in genetic multilayer feedforward neural networks, such as being unsuitable for the optimization of the weights, influencing the function of crossing operators, and so on. A concept named as “minimal schema” is proposed, based on which the coding scheme is improved. The simulation results of an example show that the improving coding is effective in optimization.关键词
遗传算法/多层前馈神经网络/编码/模式分类
信息技术与安全科学引用本文复制引用
莫鸿强,罗飞,侯小梅,毛宗源..常见遗传多层前馈神经网络实数编码的不合理性分析和改进*[J].控制理论与应用,2001,18(2):281-284,4.
