A simple neural network pruning algorithm with application to filter synthesis

Neural Processing Letters

Volumn 13, Issue 1, 2001, Pages 43-53

  Suzuki, Kenji ^a   Horiba, Isao ^a   Sugie, Noboru ^b  

^a AICHI PREFECTURAL UNIVERSITY   (Japan)

^b MEIJO UNIVERSITY   (Japan)

Author keywords

Generalization ability; Image enhancement; Neural filter; Optimal structure; Redundancy removal; Right function; Signal processing

Indexed keywords

BACKPROPAGATION; IMAGE ENHANCEMENT; LEARNING ALGORITHMS; NUMERICAL METHODS; QUANTUM ELECTRONICS; SIGNAL FILTERING AND PREDICTION; SPURIOUS SIGNAL NOISE; X RAY OPTICS;

NEURAL FILTERS; OBJECT FILTER; RIGHT FUNCTION;

MULTILAYER NEURAL NETWORKS;

EID: 0035251045     PISSN: 13704621     EISSN: None     Source Type: Journal    
DOI: 10.1023/A:1009639214138     Document Type: Article

References (19)

1. A new class of nonlinear filters - neural filters
2. Structure and properties of generalized adaptive neural filters for signal enhancement
3. Adaptive multistage weighted order statistic filters based on the back propagation algorithm
4. Comparative study on the generalized adaptive neural filter with the other nonlinear filter
5. A nonlinear digital filter using multi-layered neural networks
6. Noise reduction of medical x-ray image sequences using a neural filter with spatiotemporal inputs
7. Creating artificial neural networks that generalize
8. Neural network pruning by fusing hidden layer units
9. An iterative pruning algorithm for feedforward neural networks
10. Novel back propagation algorithm for reduction of hidden units and acceleration of convergence using artificial selection
11. Network information criterion - determining the number of hidden units for an artificial neural network model
12. A method to determine the number of hidden units of three layered neural networks by information criteria
13. Optimal brain damage
14. Generalization by weight-elimination applied to currency exchange rate prediction
15. Structural learning with forgetting
16. Generalizing smoothness constraints from discrete samples
17. Simplifying neural networks by soft weight-sharing
18. Learning internal representations by error propagation
19. Digital image restoration