Title :
Incorporating a priori knowledge into initialized weights for neural classifier
Author :
Chen, Zhe ; Feng, Tian-Jin ; Houkes, Zweitze
Author_Institution :
Dept. of Electr. Eng., Ocean Univ. of Qingdao, China
Abstract :
Artificial neural networks (ANN), especially, multilayer perceptrons (MLP) have been widely used in pattern recognition and classification. Nevertheless, how to incorporate a priori knowledge in the design of ANNs is still an open problem. The paper tries to give some insight on this topic emphasizing weight initialization from three perspectives. Theoretical analyses and simulations are offered for validation
Keywords :
learning (artificial intelligence); multilayer perceptrons; pattern classification; a priori knowledge; initialized weights; neural classifier; weight initialization; Analytical models; Artificial neural networks; Convergence; Electrostatic precipitators; Multilayer perceptrons; Nonhomogeneous media; Pattern recognition; Performance loss; Piecewise linear approximation; Piecewise linear techniques;
Conference_Titel :
Neural Networks, 2000. IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on
Conference_Location :
Como
Print_ISBN :
0-7695-0619-4
DOI :
10.1109/IJCNN.2000.857911
