Predictive minimum description length criterion for time series modeling with neural networks

M. Lehtokangas, Jukka Saarinen, P. Huuhtanen, Kimmo Kaski

Research output: Contribution to journalArticleScientificpeer-review

10 Citations (Scopus)

Abstract

Nonlinear time series modeling with a multilayer perceptron network is presented. An important aspect of this modeling is the model selection, i.e., the problem of determining the size as well as the complexity of the model. To overcome this problem we apply the predictive minimum description length (PMDL) principle as a minimization criterion. In the neural network scheme it means minimizing the number of input and hidden units. Three time series modeling experiments are used to examine the usefulness of the PMDL model selection scheme. A comparison with the widely used cross-validation technique is also presented. In our experiments the PMDL scheme and the cross-validation scheme yield similar results in terms of model complexity. However, the PMDL method was found to be two times faster to compute. This is significant improvement since model selection in general is very time consuming.
Original languageEnglish
Pages (from-to)583-593
JournalNeural Computation
Volume8
Issue number3
DOIs
Publication statusPublished - 1996
MoE publication typeA1 Journal article-refereed

Fingerprint Dive into the research topics of 'Predictive minimum description length criterion for time series modeling with neural networks'. Together they form a unique fingerprint.

Cite this