Abstract
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.
| Original language | English |
|---|---|
| Pages | 19-24 |
| Number of pages | 6 |
| Publication status | Published - 1996 Jan 1 |
| Event | Proceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4) - Washington, DC, USA Duration: 1996 Jun 3 → 1996 Jun 6 |
Other
| Other | Proceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4) |
|---|---|
| City | Washington, DC, USA |
| Period | 96-06-03 → 96-06-06 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Software
Cite this
}
Constructing stochastic networks via β-RBF networks. / Li, Sheng Tun; Leiss, Ernst L.
1996. 19-24 Paper presented at Proceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4), Washington, DC, USA, .Research output: Contribution to conference › Paper
TY - CONF
T1 - Constructing stochastic networks via β-RBF networks
AU - Li, Sheng Tun
AU - Leiss, Ernst L.
PY - 1996/1/1
Y1 - 1996/1/1
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=0029749563&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0029749563&partnerID=8YFLogxK
M3 - Paper
AN - SCOPUS:0029749563
SP - 19
EP - 24
ER -