Title :
Empirical prediction limit estimation methods for feed-forward neural networks
Author :
Chinnam, Raha Babu ; Baruah, P.
Author_Institution :
Ind. & Manuf. Eng. Dept., Wayne State Univ., Detroit, MI, USA
fDate :
6/24/1905 12:00:00 AM
Abstract :
Two empirical prediction limit (PL) estimation methods for feed-forward neural networks (FFNs) are presented. The two methods differ in one fundamental aspect: the method used for modeling the properties of the FFN model residuals. While one method uses a local approximation scheme, the other utilizes a global approximation scheme. Simulation results reveal that both methods have their relative strengths and weaknesses
Keywords :
Gaussian processes; covariance matrices; estimation theory; feedforward neural nets; function approximation; empirical prediction limit estimation methods; feed-forward neural networks; feedforward neural networks; global approximation scheme; local approximation scheme; model residuals; Approximation methods; Artificial neural networks; Covariance matrix; Digital arithmetic; Feedforward neural networks; Feedforward systems; Function approximation; Neural networks; State estimation; Testing;
Conference_Titel :
Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on
Conference_Location :
Honolulu, HI
Print_ISBN :
0-7803-7278-6
DOI :
10.1109/IJCNN.2002.1005529
