A Simple Neural Network Pruning Algorithm with Application to Filter Synthesis

  title={A Simple Neural Network Pruning Algorithm with Application to Filter Synthesis},
  author={Kenji Suzuki and Isao Horiba and Noboru Sugie},
  journal={Neural Processing Letters},
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… CONTINUE READING
36 Citations
21 References
Similar Papers


Publications referenced by this paper.
Showing 1-10 of 21 references

Noise reduction of medical x-ray image sequences using a neural ¢lter with spatiotemporal inputs

  • K. Suzuki, I. Horiba, N. Sugie, M. Nanki
  • Proc. Int. Sympo. Noise Reduction for Imaging…
  • 1998
1 Excerpt

Comparative study on the generalized adaptive neural ¢lter with the other nonlinear ¢lter

  • H. Hanek, N. Ansari, Z. Z. Zhang
  • Proc. IEEE Int. Conf. Acoustics, Speech, and…
  • 1993

Similar Papers

Loading similar papers…