Empirical estimation of generalization ability of neural networks

Research output: Contribution to journalArticle

Abstract

This work concentrates on a novel method for empirical estimation of generalization ability of neural networks. Given a set of training (and testing) data, one can choose a network architecture (number of layers, number of neurons in each layer etc.), an initialization method, and a learning algorithm to obtain a network. One measure of the performance of a trained network is how closely its actual output approximates the desired output for an input that it has never seen before. Current methods provide a "number" that indicates the estimation of the generalization ability of the network. However, this number provides no further information to understand the contributing factors when the generalization ability is not very good. The method proposed uses a number of parameters to define the generalization ability. A set of the values of these parameters provide an estimate of the generalization ability. In addition, the value of each parameter indicates the contribution of such factors as network architecture, initialization method, training data set, etc. Furthermore, a method has been developed to verify the validity of the estimated values of the parameters.

Original languageEnglish (US)
Pages (from-to)3-15
Number of pages13
JournalNeural Network World
Volume11
Issue number1
StatePublished - Jan 1 2001

Keywords

  • Artificial neural networks
  • Cross-validation
  • Error back-propagation learning
  • Feed-forward networks
  • Generalization ability
  • Voting networks

ASJC Scopus subject areas

  • Software
  • Neuroscience(all)
  • Hardware and Architecture
  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Empirical estimation of generalization ability of neural networks'. Together they form a unique fingerprint.

  • Cite this