Constructive granular systems with universal approximation and fast knowledge discovery

Authors:
Yan-Qing Zhang
Affiliations:
Dept. of Comput. Sci., Georgia State Univ., Atlanta, GA, USA
Venue:
IEEE Transactions on Fuzzy Systems
Year:
2005

Citing 0
Cited 8

Short communication: Uncertainty measures for fuzzy relations and their applications

Applied Soft Computing
Statistical fuzzy interval neural networks for currency exchange rate time series prediction

Applied Soft Computing
Hybrid attribute reduction based on a novel fuzzy-rough model and information granulation

Pattern Recognition
Genetic Granular Neural Networks

ISNN '07 Proceedings of the 4th international symposium on Neural Networks: Part II--Advances in Neural Networks
Recent Literature

Fuzzy Sets and Systems
Recent Literature Collected by Didier DUBOIS, Henri PRADE and Salvatore SESSA

Fuzzy Sets and Systems
Genetic granular cognitive fuzzy neural networks and human brains for pattern recognition

WImBI'06 Proceedings of the 1st WICI international conference on Web intelligence meets brain informatics
A Cooperative Intrusion Detection Model Based on Granular Computing and Agent Technologies

International Journal of Agent Technologies and Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

Conventional gradient descent learning algorithms for soft computing systems have the learning speed bottleneck problem and the local minima problem. To effectively solve the two problems, the n-variable constructive granular system with high-speed granular constructive learning is proposed based on granular computing and soft computing, and proved to be a universal approximator. The fast granular constructive learning algorithm can highly speed up granular knowledge discovery by directly calculating all parameters of the n-variable constructive granular system using training data, and then construct the n-variable constructive granular system with any required accuracy using a small number of granular rules. Predictive granular knowledge discovery simulation results indicate that the direct-calculation-based granular constructive algorithm is better than the conventional gradient descent learning algorithm in terms of learning speed, learning error, and prediction error.