Constructing stochastic networks via β-RBF networks

Sheng Tun Li, Ernst L. Leiss

研究成果: Paper

摘要

Without considering spatial, stochastic, and temporal features inherent in natural neural systems, the computational power of conventional artificial neural networks (ANNs) is limited. In the present paper, we look at the stochastic complexity and construct a stochastic ANN by modeling stochastic fluctuations in the environmental stimuli such that all stimuli are prone to be corrupted by noise or even outliers and to break networks down; therefore, a positive-breakdown network is required. We investigate the stochasticity in the domain of function approximation (estimation) in the framework of radial basis function networks (RBFNs) and propose a robust RBFN, β-RBFN, by applying the breakdown point approach in robust regression. Experimental results demonstrate the advantages of the proposed networks in robustness and simplicity over the plain RBFNs.

原文English
頁面19-24
頁數6
出版狀態Published - 1996 一月 1
事件Proceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4) - Washington, DC, USA
持續時間: 1996 六月 31996 六月 6

Other

OtherProceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4)
城市Washington, DC, USA
期間96-06-0396-06-06

All Science Journal Classification (ASJC) codes

  • Software

指紋 深入研究「Constructing stochastic networks via β-RBF networks」主題。共同形成了獨特的指紋。

  • 引用此

    Li, S. T., & Leiss, E. L. (1996). Constructing stochastic networks via β-RBF networks. 19-24. 論文發表於 Proceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4), Washington, DC, USA, .