Regularization with a pruning prior

Neural Networks

Volumn 10, Issue 6, 1997, Pages 1053-1059

  Goutte, Cyril ^a   Hansen, Lars Kai ^a  

^a TECHNICAL UNIVERSITY OF DENMARK   (Denmark)

Author keywords

Bayesian learning; Comparison with weight decay; Evidence framework; Generalization method; Laplace prior; Regularization

Indexed keywords

LEARNING SYSTEMS; STATISTICAL METHODS;

LAPLACE PRIOR; PRUNING PRIOR;

NEURAL NETWORKS;

ARTICLE; BRAIN MAPPING; COST BENEFIT ANALYSIS; LEARNING; MATHEMATICAL MODEL; PRIORITY JOURNAL; REGULATORY MECHANISM;

EID: 0031214394     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0893-6080(97)00027-0     Document Type: Article

References (10)

1. Akaike H. Fitting autoregressive models for prediction. Annals of the Institute of Statistical Mathematics. 21:1969;243-247.
2. Buntine W.L., Weigend A.S. Bayesian back-propagation. Complex Systems. 5:1991;603-643.
3. Goutte, C. (1996). On the use of a pruning prior for neural networks. In Neural Networks for Signal Processing VI - Proceedings of the 1996 IEEE Workshop, Number VI, NNSP. Piscataway, New Jersey: IEEE.
4. Hansen L.K., Rasmussen C.E. Pruning from adaptive regularization. Neural Computation. 6:1994;1223-1232.
5. Jaynes, E.T. (1985). Bayesian methods: general background. In J.H. Justice (Ed.), Maximum entropy and Bayesian methods in applied statistics (pp. 1-25). Cambridge: Cambridge University Press.
6. Krogh, A., & Hertz, J.A. (1992). A simple weight decay can improve generalization. In J.E. Moody, S.J. Hanson & R.P. Lippman (Eds.), Advances in neural information processing systems, Volume 4 of NIPS. Cambridge, MA: MIT.
7. Mackay D. Bayesian interpolation. Neural Computation. 4:1992;415-447.
8. Press, W.H., Teukolsky, S.A., Vetterling, W.T., & Flannery, B.P. (1992). Numerical recipes in C (2nd ed.). Cambridge: Cambridge University Press.
9. Williams P.M. Bayesian regularization and pruning using a Laplace prior. Neural Computation. 7(1):1995;117-143.
10. Wolpert, D. (1995). What Bayes has to say about the evidence procedure. In G. Heidbreder (Ed.), 1993 maximum entropy and Bayesian methods conference. Dordrecht: Kluwer.