A self-organizing neural network using fast training and pruning

Authors:
Qiao Jun-fei;Li Miao;Han Hong-gui
Affiliations:
College of Electronic and Control Engineering, Beijing University of Technology, Beijing, China;College of Electronic and Control Engineering, Beijing University of Technology, Beijing, China;College of Electronic and Control Engineering, Beijing University of Technology, Beijing, China
Venue:
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Year:
2009

Citing 7
Cited 0

Optimal brain damage

Advances in neural information processing systems 2
First- and second-order methods for learning: between steepest descent and Newton's method

Neural Computation
A quantitative model-independent method for global sensitivity analysis of model output

Technometrics
Second Order Derivatives for Network Pruning: Optimal Brain Surgeon

Advances in Neural Information Processing Systems 5, [NIPS Conference]
An integrated growing-pruning method for feedforward network training

Neurocomputing
A generalized growing and pruning RBF (GGAP-RBF) neural network for function approximation

IEEE Transactions on Neural Networks
A node pruning algorithm based on a Fourier amplitude sensitivity test method

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

A fast training and pruning algorithm is proposed for the feed-forward neural network (FNN) which consists of a fixed value subset-based training algorithm (FSBT) as well as a fast pruning algorithm (extended Fourier amplitude sensitivity test, EFAST) in this paper. The FNN is trained using FSBT, at each training iteration, only the weights of the independent nodes will be trained using the Levenberg-Marquardt (LM) algorithm, while keeping the weights of the dependent nodes unchanged. Meanwhile, the FNN is pruned using fast EFAST during training to remove redundant neurons in the hidden layer. In this way, the computational cost of the proposed EF-FNN will be reduced significantly. Experimental results suggest that the abilities of the final FNN are greatly improved. In the end, the proposed EF-FNN is used to predict the effluent water COD values; the results demonstrate the effectiveness of the proposed algorithm.