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.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Yin, L., Astola, J. and Neuvo, Y.: A new class of nonlinear filters ‐ neural filters, IEEE Trans. Signal Processing 41(3) (1993), 1201–1222.
Zhang, Z. Z. and Ansari, N.: Structure and properties of generalized adaptive neural filters for signal enhancement, IEEE Trans. Neural Networks 7(4) (1996), 857–868.
Yin, L., Astola, J. and Neuvo, Y.: Adaptive multistage weighted order statistic filters based on the back propagation algorithm, IEEE Trans. Signal Processing 42 (1994), 419–422.
Hanek, H., Ansari, N. and Zhang, Z. Z.: Comparative study on the generalized adaptive neural filter with the other nonlinear filter, Proc. IEEE Int. Conf. Acoustics, Speech, and Signal Processing, Vol. I, Minneapolis, MN, April (1993), pp. 649–652.
Arakawa, K. and Harashima, H.: A nonlinear digital filter using multi-layered neural networks, Proc. IEEE Int. Conf. Communications 2 (1990), 424–428.
Suzuki, K., Horiba, I., Sugie, N. and Nanki, M.: Noise reduction of medical x-ray image sequences using a neural filter with spatiotemporal inputs, Proc. Int. Sympo. Noise Reduction for Imaging & Commu. Systems, Tokyo, Japan, Nov. (1998), pp. 85–90.
Sietsma, J. and Dow, R. J. F.: Creating artificial neural networks that generalize, Neural Networks 4(1) (1991), 67–69.
Kameyama, K. and Kosugi, Y.: Neural network pruning by fusing hidden layer units, Trans. IEICE E 74(12) (1991), 4198–4204.
Castellano, G., Fanelli, A. M. and Pelillo, M.: An iterative pruning algorithm for feedforward neural networks, IEEE Trans. Neural Networks 8(3) (1997), 519–531.
Hagiwara, M.: Novel back propagation algorithm for reduction of hidden units and acceleration of convergence using artificial selection, Proc. Int. Joint Conf. Neural Networks II (1990), 625–630.
Murata, N., Yoshizawa, S. and Amari, S.: Network information criterion ‐ determining the number of hidden units for an artificial neural network model, IEEE Trans. Neural Networks 5(6) (1994), 865–872.
Kurita, T.: A method to determine the number of hidden units of three layered neural networks by information criteria, Trans. IEICE D-II J73-D-II(11) (1990), 1872–1878 (in Japanese).
Cun, Y. L., Denker, J. S. and Solla, S. A.: Optimal brain damage, Advances in Neural Information Processing, D.S. Touretzky (ed.), Vol. 2, (1990), pp. 598–605.
Weigend, A. S., Rumelhart, D. E. and Huberman, B. A.: Generalization by weight-elimination applied to currency exchange rate prediction, Proc. Int. Joint Conf. Neural Networks, Vol. 1, Seattle, USA, pp. 837–841, 1991.
M. Ishikawa, Structural learning with forgetting, Neural Networks 9(3) (1996), 509–521.
Ji, C., Snapp, R. R. and Psaltis, D.: Generalizing smoothness constraints from discrete samples, Neural Computation 2(1) (1990), 188–197.
Nowlan, S. J. and Hinton, G. E.: Simplifying neural networks by soft weight-sharing, Neural Computation 4(4) (1992), 473–493.
Rumelhart, D. E., Hinton, G. E. and Williams, R. J.: Learning internal representations by error propagation, Parallel Distributed Processing, Vol. 1, Chap. 8, M.I.T. Press, MA (1986), pp. 318–362.
Banham, M. R. and Katsaggelos, A. K.: Digital image restoration, IEEE Signal Processing Magazine 14(2) (1997), 24–41.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Suzuki, K., Horiba, I. & Sugie, N. A Simple Neural Network Pruning Algorithm with Application to Filter Synthesis. Neural Processing Letters 13, 43–53 (2001). https://doi.org/10.1023/A:1009639214138
Issue Date:
DOI: https://doi.org/10.1023/A:1009639214138