Incorporating a priori knowledge into initialized weights for neural classifier

Chen, Zhe and Feng, Tian-Jin and Houkes, Zweitze (2000) Incorporating a priori knowledge into initialized weights for neural classifier. In: IEEE-INNS-ENNS International Joint Conference on Neural Networks, IJCNN 2000, 24-27 July 2000, Como, Italy.

Preview

PDF
432Kb

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
Item Type:	Conference or Workshop Item
Copyright:	© 2000 IEEE Press
Research Group:	Robotics and Mechatronics (CE)
Link to this item:	http://purl.utwente.nl/publications/16331
Official URL:	http://dx.doi.org/10.1109/IJCNN.2000.857911
Export this item as:	BibTeX EndNote HTML Citation Reference Manager

Show download statistics for this publication

Repository Staff Only: item control page

Metis ID: 113216