Title :
A constructive algorithm for feedforward neural networks
Author :
Xu, Jinhua ; Ho, Daniel W. C. ; Zheng, Yufan
Author_Institution :
Inst. of Syst. Sci., East China Normal Univ., Shanghai, China
Abstract :
In this paper, a training and pruning algorithm is proposed for feedforward neural networks based on Jacobian rank deficiency. Redundant nodes are pruned during the training process, and computational cost of the training algorithm is reduced significantly. Simulations are presented to demonstrate the effectiveness of the proposed approach.
Keywords :
Jacobian matrices; feedforward neural nets; learning (artificial intelligence); Jacobian rank deficiency; computational cost; constructive algorithm; feedforward neural networks; pruning algorithm; training algorithm; Computational efficiency; Computational modeling; Feedforward neural networks; Heuristic algorithms; Jacobian matrices; Mathematics; Network topology; Neural networks; Pursuit algorithms; Redundancy;
Conference_Titel :
Control Conference, 2004. 5th Asian
Print_ISBN :
0-7803-8873-9
