Emergence of generalization in networks with constrained representations

Demetri Psaltis, Mark Neifeld

Research output: Contribution to conferencePaper

4 Scopus citations

Abstract

The authors introduce a constraint on intermediate representations which reduces the number of allowable solutions and leads to generalization for certain classes of problems. Specifically, they constrain the number of intermediate representations to be minimized during training. This representational constraint also defines a training algorithm for multilayered networks. They describe the class of problems for which the algorithm is well suited and discuss the performance of the algorithm with regard to several problems on two-layer networks.

Original languageEnglish (US)
Pages371-381
Number of pages11
DOIs
StatePublished - 1988

ASJC Scopus subject areas

  • Engineering(all)

Fingerprint Dive into the research topics of 'Emergence of generalization in networks with constrained representations'. Together they form a unique fingerprint.

  • Cite this