Parsimonious network design and feature selection through node pruning

Proceedings - International Conference on Pattern Recognition

Volumn 2, Issue , 1994, Pages 622-624

  Mao, Jianchang ^a   Mohiuddin, K ^a   Jain, Anil K ^b  

^a IBM ALMADEN RESEARCH CENTER   (United States)

^b MICHIGAN STATE UNIVERSITY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

BACKPROPAGATION; CLASSIFICATION (OF INFORMATION); FEATURE EXTRACTION;

FEATURE SELECTION METHODS; FEATURE SETS; NETWORK DESIGN; NODE PRUNING; SALIENCY MEASURE; WHITNEY;

NEURAL NETWORKS;

EID: 35848963249     PISSN: 10514651     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (5)

1. Y. leCun, J. Denker, and S. A. Solla. Optimal brain damage. In D. S. Touretzky, editor, Advances in Neural Information Processing Systems 2, pages 598-605. Morgan Kaufmann Publishers, San Mateo, CA, 1990.
2. M. C. Mozer and P. Smolensky. Skeletonization: A technique for trimming the fat from a network via relevance assessment. In D. S. Touretzky, editor, Advances in Neural Information Processing Systems 1, pages 107-115. Morgan Kaufmann Publishers, San Mateo, CA, 1989.
3. R. Reed. Pruning algorithms - a survey. IEEE Trans. Neural Networks., 4(5):740-747, Sept. 1993.
4. G. V. Trunk. A problem of dimensionality: a simple example. IEEE Trans. Pattern Anal. Machine Intell., PAMI-1(3):306-307, 1979.
5. A. Whitney. A direct method of nonparametric measurement selection. IEEE Trans. on Computers, C-20:1100-1103, 1971.