Keywords

architecture selection, cross validation, artificial neural network

Abstract

This paper studies the performance of standard architecture selection strategies, such as cost/performance and CV based strategies, for voting methods such as bagging. It is shown that standard architecture selection strategies are not optimal for voting methods and tend to underestimate the complexity of the optimal network architecture, since they only examine the performance of the network on an individual basis and do not consider the correlation between responses from multiple networks.

Original Publication Citation

Andersen, T. L. and Martinez, T. R., "Optimal Artificial Neural Network Architecture Selection for Bagging", Proceedings of the IEEE International Joint Conference on Neural Networks IJCNN'1, pp. 79-795, 21.

Document Type

Peer-Reviewed Article

Publication Date

2001-07-19

Permanent URL

http://hdl.lib.byu.edu/1877/2431

Publisher

IEEE

Language

English

College

Physical and Mathematical Sciences

Department

Computer Science

Share

COinS