Information geometry on pruning of neural network

Proceedings of 2004 International Conference on Machine Learning and Cybernetics

Volumn 6, Issue , 2004, Pages 3479-3483

  Liu, Yun Hui ^a   Luo, Si Wei ^a   Li, Ai Jun ^a   Yu, Han Bin ^a  

^a BEIJING JIAOTONG UNIVERSITY   (China)

Author keywords

Information geometry; M projection; Neural network; Pruning

Indexed keywords

ALGORITHMS; APPROXIMATION THEORY; INFORMATION ANALYSIS; PARAMETER ESTIMATION; PROBABILITY; PROBLEM SOLVING; STATISTICAL METHODS;

GEOMETRICAL NOTIONS; INFORMATION GEOMETRY; M-PROJECTION; PRUNING;

NEURAL NETWORKS;

EID: 6344261986     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (8)

1. Amari S., Differential-geometrical Method in Statistics: Lecture Notes in Statistics, Springer-Verlag, Berlin Heidelberg New York Tokyo, 1985.
2. Amari S., "Information Geometry of the EM and em Algorithm for Neural Network", Neural Network, Vol. 8, No. 9, pp. 1379-1408, Aug. 1995.
3. Giovanna Castellano, Anna Maria Fanelli, and Marcello Pelillo, "An Iterative Pruning Algorithm for Feedforward Neural Network", IEEE Trans. Neural Network, Vol. 8, No 3, pp. 519-531, May 1997.
4. Yan PF, Zhang ChSh. Artificial neural network and simulative evolution computation, Tsinghua publishing company, Beijing, 2000. (in Chinese).
5. Amari S., "Information Geometry on Hierarchy of Probability Distributions", IEEE Trans. Information Theory, Vol. 47, No. 5, pp. 1701-1711, Jul. 2001.
6. Yuhong Yang, Barron, A.R. "An asymptotic property of model selection criteria", IEEE Trans. Information Theory, Vol. 44, pp. 95-116, Jan. 1998.
7. D. Heckerman, D. Chickering. "A Comparison of Scientific and Engineering Criteria for Bayesian Model Selection", Statistics and Computing, pp.55-62. Oct. 2000.
8. A. R. Barron, J. Rissanen, and B. Yu. "The minimum description length principle in coding and modeling", IEEE Trans. Information Theory, vol.44, pp.442743-2760,Oct.1998.