A Simple Neural Network Pruning Algorithm with Application to Filter Synthesis

Authors:
Kenji Suzuki;Isao Horiba;Noboru Sugie
Affiliations:
Faculty of Information Science and Technology, Aichi Prefectural University, Nagakute, Aichi, 480–1198 Japan. E-mail: k-suzuki@ist.aichi-pu.ac.jp;Faculty of Information Science and Technology, Aichi Prefectural University, Nagakute, Aichi, 480–1198 Japan;Faculty of Science and Technology, Meijo University, Nagoya 468-0073, Japan
Venue:
Neural Processing Letters
Year:
2001

Citing 8
Cited 9

Generalizing smoothness constraints from discrete samples

Neural Computation
Learning internal representations by error propagation

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Creating artificial neural networks that generalize

Neural Networks
Optimal brain damage

Advances in neural information processing systems 2
Simplifying neural networks by soft weight-sharing

Neural Computation
Structural learning with forgetting

Neural Networks
Structure and properties of generalized adaptive neural filters for signal enhancement

IEEE Transactions on Neural Networks
An iterative pruning algorithm for feedforward neural networks

IEEE Transactions on Neural Networks

Neural Edge Detector - A Good Mimic of Conventional One Yet Robuster against Noise

IWANN '01 Proceedings of the 6th International Work-Conference on Artificial and Natural Neural Networks: Bio-inspired Applications of Connectionism-Part II
Forward and Backward Selection in Regression Hybrid Network

MCS '02 Proceedings of the Third International Workshop on Multiple Classifier Systems
Neural Edge Enhancer for Supervised Edge Enhancement from Noisy Images

IEEE Transactions on Pattern Analysis and Machine Intelligence
A novel pruning algorithm for self-organizing neural network

IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Hidden neuron pruning of multilayer perceptrons using a quantified sensitivity measure

Neurocomputing
3D virtual colonoscopy for polyps detection by supervised artificial neural networks

ICIC'11 Proceedings of the 7th international conference on Intelligent Computing: bio-inspired computing and applications
Pixel-based machine learning in medical imaging

Journal of Biomedical Imaging - Special issue on Machine Learning in Medical Imaging
Generalization capability of artificial neural network incorporated with pruning method

ADCONS'11 Proceedings of the 2011 international conference on Advanced Computing, Networking and Security
Three-and-six-month-before forecast of water resources in a karst aquifer in the Terminio massif (Southern Italy)

Applied Soft Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper describes an approach to synthesizing desired filters using a multilayer neural network (NN). In order to acquire the right function of the object filter, a simple method for reducing the structures of both the input and the hidden layers of the NN is proposed. In the proposed method, the units are removed from the NN on the basis of the influence of removing each unit on the error, and the NN is retrained to recover the damage of the removal. Each process is performed alternately, and then the structure is reduced. Experiments to synthesize a known filter were performed. By the analysis of the NN obtained by the proposed method, it has been shown that it acquires the right function of the object filter. By the experiment to synthesize the filter for solving real signal processing tasks, it has been shown that the NN obtained by the proposed method is superior to that obtained by the conventional method in terms of the filter performance and the computational cost.