| 基于模拟退火的神经网络预测模型 |
| |
| 引用本文： | 李丙春,汪仲文.基于模拟退火的神经网络预测模型[J].喀什师范学院学报,2004,25(3):63-65. |
| |
| 作者姓名： | 李丙春 汪仲文 |
| |
| 作者单位： | 1. 西北大学,计算机系,陕西,西安,710069
2. 喀什师范学院,数学系,新疆,喀什,844007 |
| |
| 摘 要： | 在分析了传统神经网络预测模型的基础上，提出用模拟退火算法代替局部梯度下降法修正网络权值，从而避免了人工神经网络容易陷入局部极小的缺陷。经实例证实，该方法能有效地提高预测的精度。
|
| 关 键 词： | 模拟退火算法 人工神经网络 预测模型 全局极小 |
| 文章编号： | 1006-432X(2004)03-0063-03 |
A Artificial Neural Network Prediction Model Based on Simulated Annealing |
| |
| LI Bing-chun,WANG Zhong-wen.A Artificial Neural Network Prediction Model Based on Simulated Annealing[J].Journal of Kashgar Teachers College,2004,25(3):63-65. |
| |
| Authors: | LI Bing-chun WANG Zhong-wen |
| |
| Institution: | LI Bing-chun~1,WANG Zhong-wen~2 |
| |
| Abstract: | After analyzing the conventional artificial neural network prediction model,we propose to modify the weight with Simulated Annealing instead of local gradient descend.Thereby, prevent the artifical neural network from resulting in local minimum. This method is able to efficiently improve the prediction accuracy by case. |
| |
| Keywords: | Simulated Annealing Neural Network Prediction Model Global Minimum |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
