摘要
将一种解决函数优化问题的混合遗传算法用于Pi-sigma神经网络的训练。这种混合算法充分利用遗传算法算法的全局搜索能力,又利用了单纯型法的局部搜索能力,因此该混合遗传算法可以使Pi-sigma神经网络更快的收敛到全局最优解,而且收敛速度比遗传算法更快。实验证明了这种算法的优越性。最后还证明了该算法可以以概率1收敛到全局最优解。
This paper uses a hybrid genetic algorithm to training Pi-sigma neural network and this algorithm is once applied to resolve a function optimizing problem.The hybrid genetic algorithm incorporates the stronger global search of genetic algorithm into the stronger local search of simplex method,and can search out the global optimum faster than genetic algorithm.The experiments show that the hybrid genetic algorithm can achieve better performance.At last,the hybrid genetic algorithm is proved converge to the global ontimum with the probability of 1.
出处
《计算机工程与应用》
CSCD
北大核心
2008年第35期56-58,共3页
Computer Engineering and Applications
基金
国家自然科学基金No.60572074~~