Constraints on generalization by adaptive networks

M. Pavel, Holly Jimison, Rebecca T. Moore

Research output: Contribution to journalArticle

Abstract

There are three classes of constraints that can be used to optimize generalization: Constraints on the network architecture, constraints on the learning algorithms, and constraints imposed by the representation of inputs and outputs. In this paper we focus on the constraints imposed by the architecture. These constraints are related to the topology of the networks, limitations on the number of units, and connectivity. In this project we used a computational approach (rather than simulation) to examine the effects of architectural constraints on generalization. Our analysis is restricted to two-layer non-recurrent networks with linear threshold units. Using this approach we characterized the effects of a variety of constraints, including minimizing the number of hidden units.

Original languageEnglish (US)
Pages (from-to)41
Number of pages1
JournalNeural Networks
Volume1
Issue number1 SUPPL
DOIs
Publication statusPublished - 1988
Externally publishedYes

    Fingerprint

ASJC Scopus subject areas

  • Artificial Intelligence
  • Neuroscience(all)

Cite this