Empirical generalization assessment of neural network models

Jan Larsen, Lars Kai Hansen

    Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

    237 Downloads (Pure)

    Abstract

    This paper addresses the assessment of generalization performance of neural network models by use of empirical techniques. We suggest to use the cross-validation scheme combined with a resampling technique to obtain an estimate of the generalization performance distribution of a specific model. This enables the formulation of a bulk of new generalization performance measures. Numerical results demonstrate the viability of the approach compared to the standard technique of using algebraic estimates like the FPE. Moreover, we consider the problem of comparing the generalization performance of different competing models. Since all models are trained on the same data, a key issue is to take this dependency into account. The optimal split of the data set of size N into a cross-validation set of size Nγ and a training set of size N(1-γ) is discussed. Asymptotically (large data sees), γopt→1 such that a relatively larger amount is left for validation
    Original languageEnglish
    Title of host publicationProceedings of the 1995 IEEE Workshop on Neural Networks for Signal Processing
    PublisherIEEE
    Publication date1995
    Pages30-39
    ISBN (Print)07-80-32739-X
    DOIs
    Publication statusPublished - 1995
    Event1995 IEEE Workshop on Neural Networks for Signal Processing V - Cambridge, MA, United States
    Duration: 31 Aug 19952 Sep 1995
    Conference number: 5
    http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=3947

    Workshop

    Workshop1995 IEEE Workshop on Neural Networks for Signal Processing V
    Number5
    CountryUnited States
    CityCambridge, MA
    Period31/08/199502/09/1995
    Internet address

    Bibliographical note

    Copyright 1995 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE

    Fingerprint Dive into the research topics of 'Empirical generalization assessment of neural network models'. Together they form a unique fingerprint.

    Cite this