Optimization of neural networks: A comparative analysis of the genetic algorithm and simulated annealing
Optimization of neural networks: A comparative analysis of the genetic algorithm and simulated annealing
复制标题
DOI：
10.1016/s0377-2217(98)00114-3
复制
发表时间：
1999-05-01
影响因子：
6.4
通讯作者：
Johnson, JD
中科院分区：
文献类型：
--
作者：
Sexton, RS;Dorsey, RE;Johnson, JD
神经网络作为一种工具，能够将未知函数近似到任何所需的精度，这使得神经网络在商业领域的研究不断升级。尽管基于梯度的搜索技术（诸如反向传播）是目前用于训练神经网络的最广泛使用的优化技术，但是已经表明，这些梯度技术在找到全局解的能力方面受到严重限制。全球搜索技术已被确定为解决这一问题的一个潜在的解决方案。在本文中，我们研究了两个著名的全局搜索技术，模拟退火和遗传算法，并比较它们的性能。进行了蒙特卡罗研究，以测试这些全局搜索技术优化神经网络的适当性。(C)1999 Elsevier Science B.V.保留所有权利。
The escalation of Neural Network research in Business has been brought about by the ability of neural networks, as a tool, to closely approximate unknown functions to any degree of desired accuracy. Although, gradient based search techniques such as back-propagation are currently the most widely used optimization techniques for training neural networks, it has been shown that these gradient techniques are 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 we examine two well known global search techniques, Simulated Annealing and the Genetic Algorithm, and compare their performance. A Monte Carlo study was conducted in order to test the appropriateness of these global search techniques for optimizing neural networks. (C) 1999 Elsevier Science B.V. All rights reserved.