Title :
Training Feedforward Neural Networks by Pruning Algorithm Based on Grey Incidence Analysis
Author :
Xiong, Yan ; Wang, Li ; Li, Dawei
Author_Institution :
Sch. of Sci., Univ. of Sci. & Technol., Anshan
Abstract :
In this paper, a new pruning algorithm based on grey incidence analysis for feedforward neural networks is presented.The pruned network has the optimal topology with avoiding over training and obtaining good generalization.The removed connections and the incorporated connections are chosen according to the degree of grey incidence of each output sequence of the network units. The simulation results show the effectiveness over several test problems.
Keywords :
feedforward neural nets; grey systems; learning (artificial intelligence); feedforward neural network training; grey incidence analysis; pruning algorithm; topology; Agricultural engineering; Algorithm design and analysis; Data engineering; Feedforward neural networks; Industrial training; Information analysis; Information technology; Intelligent networks; Network topology; Neural networks; feedforward neural network; grey incidence analysis; least-squares method; pruning algorithm;
Conference_Titel :
Intelligent Information Technology Application, 2008. IITA '08. Second International Symposium on
Conference_Location :
Shanghai
Print_ISBN :
978-0-7695-3497-8
DOI :
10.1109/IITA.2008.125
