Numerical Learning Method for Process Neural Network

Authors:
Tianshu Wu;Kunqing Xie;Guojie Song;Xingui He
Affiliations:
Key laboratory of Machine Perception, Ministry of Education, Peking University, Beijing, China 100871;Key laboratory of Machine Perception, Ministry of Education, Peking University, Beijing, China 100871;Key laboratory of Machine Perception, Ministry of Education, Peking University, Beijing, China 100871;Key laboratory of Machine Perception, Ministry of Education, Peking University, Beijing, China 100871
Venue:
ISNN '09 Proceedings of the 6th International Symposium on Neural Networks on Advances in Neural Networks
Year:
2009

Citing 9
Cited 1

Approximation and radial-basis-function networks

Neural Computation
Fuzzy neural networks: a survey

Fuzzy Sets and Systems
A Mixed Process Neural Network and its Application to Churn Prediction in Mobile Communications

ICDMW '06 Proceedings of the Sixth IEEE International Conference on Data Mining - Workshops
An Improved Fuzzy Neural Network for Ultrasonic Motors Control

ISNN '07 Proceedings of the 4th international symposium on Neural Networks: Advances in Neural Networks
Data Fusion Based on Neural Networks and Particle Swarm Algorithm and Its Application in Sugar Boiling

ISNN '08 Proceedings of the 5th international symposium on Neural Networks: Advances in Neural Networks
A Hybrid Model of Partial Least Squares and RBF Neural Networks for System Identification

ISNN '08 Proceedings of the 5th international symposium on Neural Networks: Advances in Neural Networks
Data management by self-organizing maps

WCCI'08 Proceedings of the 2008 IEEE world conference on Computational intelligence: research frontiers
Worm harm prediction based on segment procedure neural networks

RSKT'06 Proceedings of the First international conference on Rough Sets and Knowledge Technology
Complex number procedure neural networks

ICNC'05 Proceedings of the First international conference on Advances in Natural Computation - Volume Part I

Particle swarm optimization based learning method for process neural networks

ISNN'10 Proceedings of the 7th international conference on Advances in Neural Networks - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

Process neural network (PNN) dealing with process inputs is widely used. Currently, the learning method of PNN is mainly based on base functions expansion. However, selecting base functions and their parameters is much difficult, and moreover, the corresponding learning method is time consuming due to integral with numbers of base functions. A numerical learning method (NL) for PNN was proposed in this study. It represented PNN's inputs and weights functions in numerical forms and trained the network in a numerical way so that NL avoided the selections of base functions and their parameters. Experiments showed that NL based PNN was more accurate and had lower computation complexity.