Invariance priors for Bayesian feed-forward neural networks

Neural Networks

Volumn 19, Issue 10, 2006, Pages 1550-1557

  Toussaint, Udo v ^a   Gori, Silvio ^a   Dose, Volker ^a  

^a MAX PLANCK INSTITUT FÜR PLASMAPHYSIK   (Germany)

Author keywords

Bayesian; Evidence; Model selection; Multilayer perceptron; Prior; Pruning; Regularization; Transformation invariance

Indexed keywords

COMPUTATIONAL METHODS; INVARIANCE; MATHEMATICAL MODELS; MATHEMATICAL TRANSFORMATIONS; PROBABILITY;

BAYESIAN MODELS; MODEL SELECTION; MULTILAYER PERCEPTRON; TRANSFORMATION INVARIANCE;

FEEDFORWARD NEURAL NETWORKS;

ARTICLE; ARTIFICIAL NEURAL NETWORK; AUTOMATION; BAYES THEOREM; ENTROPY; MATHEMATICAL ANALYSIS; MATHEMATICAL MODEL; MONTE CARLO METHOD; POSITIVE FEEDBACK; PRIORITY JOURNAL;

ALGORITHMS; BAYES THEOREM; COMPUTER SIMULATION; MODELS, NEUROLOGICAL; NEURAL NETWORKS (COMPUTER); NEURONS; NONLINEAR DYNAMICS;

EID: 33751203854     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.neunet.2006.01.017     Document Type: Article

References (19)

1. Berger E., et al. Approach for the evaluation of speckle deformation measurements by application of the wavelet transformation. Applied Optics 36 (1997) 7455-7460
2. Berger E., et al. Reconstruction of surfaces from phase-shifting speckle interferometry. Applied Optics 38 (1999) 4997-5003
3. Bishop C.M. Neural networks for pattern recognition (1995), Oxford University Press
4. Box G.E.P., and Tiao G.C. Bayesian inference in statistical analysis (1973), Addison-Wesley, Reading, MA
5. Buck B., and Macaulay V.A. Maximum entropy in action (1991), Oxford University Press
6. Dose V. Hyperplane priors. In: Williams C.J. (Ed). Bayesian inference and maximum entropy methods in science and engineering: 23rd international workshop (2003), AIP, Melville, NY 350-357
7. Goutte C., and Hansen L.K. Regularization with a pruning prior. Neural Networks 10 6 (1997) 1053-1059
8. Jaynes E.T. Prior probabilities. In: Rosenkrantz R. (Ed). Papers on probability, statistics and statistical physics (1983), Reidel, Dordrecht, The Netherlands
9. Lampinen J., and Vehtari A. Bayesian approach for neural networks. Neural Networks 14 (2001) 257-274
10. Landau L.D., and Lifschitz E.M. Lehrbuch der Theoretischen Physik I (1962), Akademie Verlag, Berlin
11. Leonard T., and Hsu J.S.J. Bayesian methods: An analysis for statisticians and interdisciplinary researchers (1999), Cambridge University Press, Cambridge
12. Mackay D.J.C. A practical Bayesian framework for backpropagation networks. Neural Computation 4 3 (1992) 448-472
13. NAG LTD (2003). Optimization routine nag_nlp_sol, mark18. Oxford, OX2 8DR, UK. http://www.nag.co.uk
14. Neal, R. M. (1992). Bayesian training of backpropagation networks, Technical report CRG-TR-92-1. Department of Computer Science, University of Toronto
15. Penny W.D., and Roberts S.J. Bayesian neural networks for classification. Neural Networks 12 (1999) 877-892
16. Sivia D. Data analysis: A Bayesian tutorial (1996), Oxford University Press
17. Thodberg H.H. A review of Bayesian neural networks with an application to near infrared spectroscopy. IEEE Transactions on Neural Networks 7 1 (1995) 56-72
18. Williams P.M. Bayesian regularization and pruning using a Laplace prior. Neural Computation 7 (1995) 117-143
19. Williams P.M. Matrix logarithm parametrizations for neural network covariance models. Neural Networks 12 (1999) 299-308