A mean field algorithm for Bayes learning in large feed-forward neural networks

Advances in Neural Information Processing Systems

Volumn , Issue , 1997, Pages 225-231

  Opper, Manfred ^a   Winther, Ole ^b  

^a UNIVERSITY OF WÜRZBURG   (Germany)

^b UNIVERSITY OF COPENHAGEN   (Denmark)

Author keywords

[No Author keywords available]

Indexed keywords

FORECASTING; STATISTICAL MECHANICS; STATISTICAL METHODS;

BAYES-OPTIMAL; DISORDERED SYSTEM; FEED-FORWARD NETWORK; LEAVE-ONE-OUT CROSS VALIDATIONS; MEAN FIELD; MEAN FIELD METHODS; SINGLE LAYER PERCEPTRON;

ALGORITHMS;

EID: 84898996834     PISSN: 10495258     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (7)

1. Berger, J. O. (1985) Statistical Decision theory and Bayesian Analysis, Springer-Verlag, New York.
2. MacKay. D.J. (1992) A practical Bayesian framework for backpropagation networks, Neural Com p. 4 448.
3. Mezard, M., Parisi G. & Virasoro M. A. (1987) Spin Glass Theory and Beyond, Lecture Notes in Physics, 9, World Scientific, .
4. Mezard, M. (1989) The space of interactions in neural networks: Gardner's calculation with the cavity method J. Phys. A 22, 2181 .
5. Opper, M. & Haussler, D. (1991) in IVth Annual Workshop on Computational Learning Theory (COLT91), Morgan Kaufmann.
6. Opper M. & Winther O (1996) A mean field approach to Bayes learning in feedforward neural networks, Phys. Rev. Lett. 76 1964.
7. Thouless, D.J., Anderson, P. W. & Palmer, R.G. (1977), Solution of 'Solvable model of a spin glass' Phil. Mag. 35, 593.