Emergence of generalization in networks with constrained representations

Demetri Psaltis, Mark A Neifeld

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

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)
Title of host publicationIEEE Int Conf on Neural Networks
PublisherPubl by IEEE
Pages371-381
Number of pages11
StatePublished - 1988
Externally publishedYes

Fingerprint

Network layers

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Psaltis, D., & Neifeld, M. A. (1988). Emergence of generalization in networks with constrained representations. In IEEE Int Conf on Neural Networks (pp. 371-381). Publ by IEEE.

Emergence of generalization in networks with constrained representations. / Psaltis, Demetri; Neifeld, Mark A.

IEEE Int Conf on Neural Networks. Publ by IEEE, 1988. p. 371-381.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Psaltis, D & Neifeld, MA 1988, Emergence of generalization in networks with constrained representations. in IEEE Int Conf on Neural Networks. Publ by IEEE, pp. 371-381.
Psaltis D, Neifeld MA. Emergence of generalization in networks with constrained representations. In IEEE Int Conf on Neural Networks. Publ by IEEE. 1988. p. 371-381
Psaltis, Demetri ; Neifeld, Mark A. / Emergence of generalization in networks with constrained representations. IEEE Int Conf on Neural Networks. Publ by IEEE, 1988. pp. 371-381
@inproceedings{d1ca0767b34646cd920059a32db5c132,
title = "Emergence of generalization in networks with constrained representations",
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.",
author = "Demetri Psaltis and Neifeld, {Mark A}",
year = "1988",
language = "English (US)",
pages = "371--381",
booktitle = "IEEE Int Conf on Neural Networks",
publisher = "Publ by IEEE",

}

TY - GEN

T1 - Emergence of generalization in networks with constrained representations

AU - Psaltis, Demetri

AU - Neifeld, Mark A

PY - 1988

Y1 - 1988

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=0024122889&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0024122889&partnerID=8YFLogxK

M3 - Conference contribution

SP - 371

EP - 381

BT - IEEE Int Conf on Neural Networks

PB - Publ by IEEE

ER -