Estimation of generalization capability by combination of new information criterion and cross validation

9 December 2002

conference paper
Published by Institute of Electrical and Electronics Engineers (IEEE)

Vol. ii, 1-6
https://doi.org/10.1109/ijcnn.1991.155303

Abstract

The authors propose a novel method of selecting the optimal neural network structure with maximum generalization capability. By expanding Akaike's information criterion, they propose a new information criterion that can estimate generalization capability without the maximum likelihood estimator of synaptic weights. The cross validation method is used to calculate the new information criterion. Computer simulation shows that the proposed information criterion can accurately predict the generalization capability of multilayer perceptrons, and thus the optimal number of hidden units can be determined.<>

Keywords

This publication has 7 references indexed in Scilit:

Learning from examples in large neural networks
Physical Review Letters, 1990
The Vapnik-Chervonenkis Dimension: Information versus Complexity in Learning
Neural Computation, 1989
What Size Net Gives Valid Generalization?
Neural Computation, 1989
On the approximate realization of continuous mappings by neural networks
Neural Networks, 1989
Consistent inference of probabilities in layered networks: predictions and generalizations
Published by Institute of Electrical and Electronics Engineers (IEEE) ,1989
Capabilities of three-layered perceptrons
Published by Institute of Electrical and Electronics Engineers (IEEE) ,1988
A new look at the statistical model identification
IEEE Transactions on Automatic Control, 1974