摘要
提出并研究了一种优化设计求解的遗传神经网络新算法,该算法综合了遗传算法的全局性和神经网络的并行快速性等特点,可克服遗传算法最终进化至最优解较慢和神经网络易陷入局部解的缺陷。
A genetic neural network algorithm for optimum design is developed. In the algorithm, the global property of genetic algorithms (AG) and the parallelism of artificial neural networks (AN 2) are combined; GA provides global initial solutions, from which AN 2 obtains the final solutions. Thus, the defects of slow convergence with GA and easily falling into local solutions with AN 2 can be overcome. An applied example shows that the global property of the new algorithm is better than that of AN 2, and its convergence is better than that of GA.
出处
《西南交通大学学报》
EI
CSCD
北大核心
2000年第1期65-68,共4页
Journal of Southwest Jiaotong University
基金
国家自然科学基金资助项目! ( 5 96 85 0 0 3 )
四川省跨世纪青年学科带头人培养基金
关键词
神经网络
遗传算法
计算智能
优化设计
算法
neural networks
genetic algorithms
computing intelligence
optimum design