A new model selection criterion based on information geometry

2004 7th International Conference on Signal Processing Proceedings, ICSP

Volumn , Issue , 2004, Pages 1561-1564

  Liu, Yunhui ^a   Luo, Siwei ^a   Li, Aijun ^a   Yu, Hanbin ^a  

^a BEIJING JIAOTONG UNIVERSITY   (China)

Author keywords

Geometric complexity; Geometric fitness; Information geometry; Model selection

Indexed keywords

COMPUTATIONAL COMPLEXITY; INFORMATION ANALYSIS; MATHEMATICAL MODELS; NEURAL NETWORKS; PROBABILITY DISTRIBUTIONS; STOCHASTIC CONTROL SYSTEMS;

GEOMETRIC COMPLEXITY; GEOMETRIC FITNESS; INFORMATION GEOMETRY; MODEL SELECTION;

COMPUTATIONAL GEOMETRY;

EID: 10444281569     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (11)

1. Myung, I. J., Balasubramanian,V., Pitt, M. A. Counting Probability Distributions: Differential Geometry and Model Selection. Proceedings of the National Academy of Science USA, 1997, 11170-11175.
2. Yan PF, Zhang ChSh. Artificial neural network and simulative evolution computation, Tsinghua publishing company, 2000, 83-85, (in Chinese).
3. Yuhong Yang, Barron, A.R. An asymptotic property of model selection criteria. IEEE Transactions on Information Theory, Vol. 44, Jan. 1998, 95-116.
4. D. Heckerman. A Comparison of Scientific and Engineering Criteria for Bayesian Model Selection. Statistics and Computing, 2000, 10,55-62.
5. Rissanen, J. Fisher information and stochastic complexity. IEEE Trans. on Inf., 42, 1996,40-47.
6. Bozdogan, H. On the Information-based Measure of Covariance Complexity and its Application to the Evaluation of Multivariate Linear Models. Communications in Statistics, Theory and Methods, A19 No. 1, 1990, 221-278.
7. A. R. Barron, J. Rissanen, and B. Yu. The minimum description length principle in coding and modeling. IEEE Transactions on Information Theory, vol. 44, Oct. 1998,2743-2760.
8. Bojan Kverh,Tomas Pajdla. Analysis of Different Model Selection Criteria. Technical Report, http://citeseer.nj.nec.com/kverh99analysis.html.
9. Amari. Differential Geometrical Method in Statistics, Berlin, Springer, 1985.
10. Luo SW, Wen JW. Research and Analysis of Neural Field Global Architecture and Increase Ability. Journal of Computer Research and Development, Vol.40,No.5, 2003, 668-674, (in Chinese).
11. Huaiyu Zhu, Richard Rohwer. Information Geometric Measurements of Generalisation. Technical Report NCRG/4350,Aug. 1995.