【摘要】 神经网络有以任意精度逼近未知函数的能力 ,所以被广泛应用于各种领域中。目前广泛应用于神经网络优化的方法是反向传播 (BackPropagation ,BP) ,但是BP的全局搜索能力很有限 ,而全局搜索方法是神经网络优化问题很有潜力的办法。文中研究了两种全局优化算法 :遗传算法 (GeneticAlgorithm ,GA)和模拟退火 (SimulatedAnnealing,SA) ,并且比较了它们在神经网络优化中的性能。更多还原

【Abstract】 The neural network has the ability to closely approximate unknown functions to any degree of desired accuracy, so it apply to various kinds of fields extensively. Today, Back-propagation(BP) is the most widely used optimization techniques for training neural networks, it has been shown that BP severely limited in their ability to find global solutions, global search techniques have been identified as a potential solution to this problem. In this paper, the authors examine two global search techniques: Genetic Algorithm and Simulated Annealing, and also compare their performance for optimizing neural networks.更多还原