Title :
Classified forgetting neural network and its effectiveness analysis
Author :
Yan, Chang-Shun ; Li, Yi-Jun
Author_Institution :
Sch. of Manage., Harbin Inst. of Technol., China
Abstract :
The available classification method of neural network lacks the ability to deal with data of different variable time. Based on it, the paper puts the forgetting ideology into the classification method of neural network, and successfully brings up classified forgetting neural network model. In the end, the paper proves the effectiveness of using this model to classify random time changing data by experiment.
Keywords :
data analysis; learning (artificial intelligence); neural nets; pattern classification; classified forgetting neural network; effectiveness analysis; forgetting coefficient; network training; random time changing data classification; Data analysis; Databases; Electronic mail; Error correction; Feedforward neural networks; Humans; Neural networks; Organizing; Technology management; Training data; Classified forgetting neural network; forgetting coefficient; network training;
Conference_Titel :
Machine Learning and Cybernetics, 2005. Proceedings of 2005 International Conference on
Conference_Location :
Guangzhou, China
Print_ISBN :
0-7803-9091-1
DOI :
10.1109/ICMLC.2005.1527646
