| 训练模式对的摄动对单体模糊神经网络的影响 |
| |
| 引用本文： | 何春梅,叶有培,徐蔚鸿. 训练模式对的摄动对单体模糊神经网络的影响[J]. 南京理工大学学报(自然科学版), 2009, 33(1) |
| |
| 作者姓名： | 何春梅 叶有培 徐蔚鸿 |
| |
| 作者单位： | 1. 南京理工大学,计算机科学与技术学院,江苏,南京,210094
2. 长沙理工大学,计算机与通信工程学院,湖南,长沙,410077 |
| |
| 摘 要： | 针对训练模式对的小幅摄动可能对模糊神经网络的性能产生不利影响,提出了单体模糊神经网络对训练模式对摄动的鲁棒性概念,并就训练模式对的最大保序摄动的情形对单体模糊神经网络(MFNN)进行了具体分析,一般的模糊神经网络对训练模式对摄动的鲁棒性概念可类似定义.理论研究表明:当训练模式对发生最大γ保序摄动时,在h=5的条件下,单体模糊神经网络对训练模式对的摄动全局拥有好的鲁棒性,这将有助于MFNN系统的性能分析、学习算法的选择和模式对获取.
|
| 关 键 词： | 单体模糊神经网络 学习算法 摄动 训练模式对 鲁棒 |
Influences of Perturbation of Training Pattern Pairs on Monolithic Fuzzy Neural Networks |
| |
| HE Chun-mei,YE You-pei,XU Wei-hong. Influences of Perturbation of Training Pattern Pairs on Monolithic Fuzzy Neural Networks[J]. Journal of Nanjing University of Science and Technology(Nature Science), 2009, 33(1) |
| |
| Authors: | HE Chun-mei YE You-pei XU Wei-hong |
| |
| Affiliation: | 1.School of Computer Science and Technology;NUST;Nanjing 210094;China;2.School of Computer andCommunication Engineering;Changsha University of Science and Technology;Changsha 410077;China |
| |
| Abstract: | Small perturbations of training pattern pairs may cause some disadvantages to performance of a fuzzy neural network(FNN),and a new concept is established for the robustness of a monolithic fuzzy neural network(MFNN) to perturbations of training pattern pairs.When the training pattern pairs come into the keep-order perturbations,the robustness of MFNN model is analyzed.The concept for the robustness of a FNN to perturbations of training pattern pairs can be defined similarly.The theoretical studies show that... |
| |
| Keywords: | monolithic fuzzy neural networks learning algorithms perturbation training pattern pairs robustness |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
