Invariance priors for Bayesian feed-forward neural networks

Authors:
Udo v. Toussaint;Silvio Gori;Volker Dose
Affiliations:
Centre for Interdisciplinary Plasma Science, Max-Planck-Institut für Plasmaphysik, EURATOM Association, Boltzmannstr. 2, D-85748 Garching, Germany;Centre for Interdisciplinary Plasma Science, Max-Planck-Institut für Plasmaphysik, EURATOM Association, Boltzmannstr. 2, D-85748 Garching, Germany;Centre for Interdisciplinary Plasma Science, Max-Planck-Institut für Plasmaphysik, EURATOM Association, Boltzmannstr. 2, D-85748 Garching, Germany
Venue:
Neural Networks
Year:
2006

Citing 7
Cited 2

A practical Bayesian framework for backpropagation networks

Neural Computation
Bayesian regularization and pruning using a Laplace prior

Neural Computation
Regularization with a pruning prior

Neural Networks
Matrix logarithm parametrizations for neural network covariance models

Neural Networks
Bayesian neural networks for classification: how useful is the evidence framework

Neural Networks
Bayesian approach for neural networks—review and case studies

Neural Networks
A review of Bayesian neural networks with an application to near infrared spectroscopy

IEEE Transactions on Neural Networks

A generalized-constraint neural network model: Associating partially known relationships for nonlinear regressions

Information Sciences: an International Journal
MML logistic regression with translation and rotation invariant priors

AI'12 Proceedings of the 25th Australasian joint conference on Advances in Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

Neural networks (NN) are famous for their advantageous flexibility for problems when there is insufficient knowledge to set up a proper model. On the other hand, this flexibility can cause overfitting and can hamper the generalization of neural networks. Many approaches to regularizing NN have been suggested but most of them are based on ad hoc arguments. Employing the principle of transformation invariance, we derive a general prior in accordance with the Bayesian probability theory for feed-forward networks. An optimal network is determined by Bayesian model comparison, verifying the applicability of this approach. Additionally the prior presented affords cell pruning.