| 引用本文: | 汪秉文, 沈艳军, 何统洲.多输出神经元模型的多层前向神经网络及其应用[J].控制理论与应用,2004,21(4):611~613.[点击复制] |
| WANG Bing-wen, SHEN Yan-jun, HE Tong-zhou.Multilayer feedforward neural networkswith multioutput neural model and its application[J].Control Theory and Technology,2004,21(4):611~613.[点击复制] |
|
| 多输出神经元模型的多层前向神经网络及其应用 |
| Multilayer feedforward neural networkswith multioutput neural model and its application |
| 摘要点击 1586 全文点击 1900 投稿时间：2003-02-19 修订日期：2003-06-26 |
| 查看全文 查看/发表评论 下载PDF阅读器 |
| DOI编号 10.7641/j.issn.1000-8152.2004.4.026 |
| 2004,21(4):611-613 |
| 中文关键词 神经网络 神经元模型 递推最小二乘算法 多输出神经元模型 |
| 英文关键词 neural networks neural model recurrent least square(RLS) multi_output neural model |
| 基金项目 |
|
| 中文摘要 |
| 研究了一种新的多输出神经元模型.首先,给出这类模型的一般形式,并将该模型应用于多层前向神经网络;其次,给出了其学习算法,即递推最小二乘算法,最后通过几个模拟实验表明,采用多输出神经元模型的多层前向神经网络,具有结构简单,泛化能力强,收敛速度快,收敛精度高等特点,其性能远远优于激活函数可调模型的多层前向神经网络. |
| 英文摘要 |
| A multi_output neural model and its general form are presented.The recurrent least square,a learning algorithm,was used to train multilayer feedforward neural networks(MFNN) with this new model.Several simulations demonstrated that MO (multi_output neural)_MFNN has simple architecture, excellent generalization capacity, fast speed of convergence and improved accuracy. Its performance is superior to TAF (tunable activation function) MFNN. |
|
|
|
|
|