| 基于二元蚁群算法的多层前馈神经网络 |
| |
| 引用本文： | 魏 平,熊伟清,江宝钏. 基于二元蚁群算法的多层前馈神经网络[J]. 计算机工程与应用, 2007, 43(26): 68-71 |
| |
| 作者姓名： | 魏 平 熊伟清 江宝钏 |
| |
| 作者单位： | 宁波大学,计算机科学与技术研究所,浙江,宁波,315211;宁波大学,计算机科学与技术研究所,浙江,宁波,315211;宁波大学,计算机科学与技术研究所,浙江,宁波,315211 |
| |
| 基金项目： | 国家自然科学基金 , 浙江省自然科学基金 |
| |
| 摘 要： | 提出了一种基于二元蚁群算法的多层前馈神经网络,同时为了避免二元蚁群算法陷入局部最优引入了拥挤交通组织策略。将二元蚁群算法和神经网络混合,可兼有神经网络广泛映射能力和二元蚁群算法快速全局收敛能力,通过在函数逼近实验表明取得了较好的结果。
|
| 关 键 词： | 二元蚁群算法 前馈神经网络 拥挤交通组织 反向传播算法 函数逼近 |
| 文章编号： | 1002-8331（2007）26-0068-04 |
| 修稿时间： | 2007-05-01 |
Multi-layer feedforward neural network based on binary ant colony algorithms |
| |
| WEI Ping,XIONG Wei-qing,JIANG Bao-chuan. Multi-layer feedforward neural network based on binary ant colony algorithms[J]. Computer Engineering and Applications, 2007, 43(26): 68-71 |
| |
| Authors: | WEI Ping XIONG Wei-qing JIANG Bao-chuan |
| |
| Affiliation: | Institute of Computer Science and Technology,Ningbo University,Ningbo,Zhejiang 315211,China |
| |
| Abstract: | Multi-layer feedforward neural network based on binary ant colony algorithms is designed.At the same time the crowded traffic organization tactics is introduced to avoid the convergence to the local minimum points.The combination of binary colony algorithms with the neural network can have both extensive mapping ability of neural network and rapid global convergence ability of binary ant colony algorithms.The result shows better by the example of function approaching. |
| |
| Keywords: | binary ant colony algorithms feedforward neural network crowded traffic organization tactics back-propagation function approaching |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《计算机工程与应用》浏览原始摘要信息 |
|
点击此处可从《计算机工程与应用》下载免费的PDF全文 |
|
