期刊文献+

模块化神经网络集成方法研究 被引量:1

Research on Integration Method for Modular Neural Network
下载PDF
导出
摘要 针对模块化神经网络的集成问题,综合"分而治之"和"集思广益"的思想,提出了一种在线选择子网络的方法。针对不同的输入,计算输入与各子网络训练样本中心的距离测度,构造距离测度的隶属函数,通过模糊判别实现子网络的在线选择。参与信息处理的子网络随输入变化,使网络集成具有更强的自适应能力。多个子网络采用线性整合,采用样本空间重构技术及动态规划方法实现子网络权重的在线优化。仿真结果表明:该方法提高了模块化神经网络的精度和泛化能力。 To solve intergration problem of modular neural network (MNN), the measure of online sub-networks selection is proposed with integrating ideas of “divide and conquer” and “brainstorm”. According to different inputs, distance measurement between inputs and each center of sub-networks training sample is calculated to construct subordination function, and to realize online sub-networks selection by fuzzy judgement. The change of sub-networks involved in information processing with inputs makes self-adapting ability stronger for network integration. Many sub-networks are intergrated by linear method. Online optimization of weights of sub-networks are realized by reconstructing technology of sample space and dynamic programming. Simulation results show precision and generalization ability of MNN are improved effectively.
出处 《石油化工自动化》 CAS 2014年第4期41-46,共6页 Automation in Petro-chemical Industry
关键词 模块化神经网络 分而治之 权重优化 modular neural network divide and conquer weight optimization
  • 相关文献

参考文献11

  • 1JACOBS R A, JORDAN M A. Modular Connectionist Architecture for learning Piecewise Control Strategies[C]. America: Proceedings of the American Control Conference. 1991: 343-351.
  • 2SUN Jianzhong, ZUO Hongfu, YANG Haibin. Study of Ensemble Learning-Based Fusion Prognostics [ C ]. Prognostics and Health Management Conference, 2010.
  • 3GANGARDlWALA A, POLIKAR R. Dynamically Weighted Majority Voting for Incremental Learning and Comparison of Three Boosting Based Approaches [ C].Canada: Proceedings of International Joint Conference on Neural Networks. 2005.
  • 4GAO Daqi. Clas~modular Multi-layer Perceptions, Task De-composition and Virtually Balanced Training Subsets [C]. Florida: Proceedings of International Joint Con{erence on Neural Networks. 2007.
  • 5MARIO G C A, WITOLD P, BEATRICE L, et al. Using Muhilayer Pereeptrons as Receptive Fields in the Design of Neural Networks [J]. Neurocomputing, 2009(72): 2536 - 2548.
  • 6ZHOU Zhihua, WU Jianxin, WEI Tang. Ensembling Neural Networks Many Could be Better Than All[J]. Artificial Intelligence, 2002(137) : Z39 - 263.
  • 7WITOLD P, GEORGE V. Granular Neural Networks [J]. Neurocomputing, 2001(36) : 205 - 224.
  • 8王攀,李幼凤,范衠,冯帅.模块化神经网络子网的动态集成方法学研究[J].系统工程与电子技术,2008,30(6):1143-1147. 被引量:2
  • 9ZHOU Zhihua, WU Jianxin, WEI Tang. Combining Regression Estimators.. GA-Based Selective Neural Network Ensemble [J]. International Journal of Computational Intelligence and Applications, 2001, 1(04) 341 - 356.
  • 10王正群,陈世福,陈兆乾.并行学习神经网络集成方法[J].计算机学报,2005,28(3):402-408. 被引量:36

二级参考文献35

  • 1王攀.科技创新中的方法集成及其范例——软计算方法集成[J].中国软科学,2007(1):139-143. 被引量:3
  • 2Lu B., Kita H., Nishikawa Y.. A multi-sieving neural network architecture that decomposes learning tasks automatically. In: Proceedings of the World Congress on Computational Intelligence, Florida, USA, 1994, 3: 1319~1324
  • 3Takagi H., Suzuki N., Toshiyukikoda, Kojima Y.. Neural networks designed on approximate reasoning architecture and their applications. IEEE Transactions on Neural Networks, 1992, 3(5): 752~760
  • 4Auda G., Kamel M.. CMNN: Cooperative modular neural networks. In: Proceedings of International Conference Neural Networks, 1997, 2: 226~231
  • 5Moody J.O., Antsaklis P.J.. The dependence identification neural network construction algorithm. IEEE Transactions on Neural Networks, 1996, 7(1): 3~15
  • 6Ling Wei-Xin, Zheng Qi-Lun, Chen Qiong, Lv Cui-Ying. PCMNN: A parallel cooperative modularied neural network architecture. In: Proceedings of the 10th IEEE International Conference on Fuzzy Systems, 2001, 1: 268~271
  • 7Hornik K., Stinchcombe M., White H.. Mutilayer feedforward networks are universal approximators. Neural Networks, 1989, 2: 359~366
  • 8Hunt H., Sbarbaro D., Zbikowski R.. Neutral networks for control system--A survey. Automatica, 1992, 28(6): 1083~1112
  • 9Weston A.E.J., Stitson M.O., Gammerman A.. Experiments with support vector machines. Royal Holloway University, London: Technical Report CSD-TR-96-19, 1996
  • 10Auda G, Kamel M. Modular neural networks., a survey [J]. International J on Neural Systems, 1999, 9 (2) : 129 - 151.

共引文献39

同被引文献6

引证文献1

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部