PATTERN RECOGNITION BY CONVOLUTION POLYNOMIAL.

Michael P. Remler

Research output: Contribution to journalArticle

Abstract

Pattern recognition is considered as a mapping from the set of all inputs to the numbers 0 to 1. The inputs are treated as vectors. A topological group algebra over the vector space is described. The input is treated as a variable in a polynomial of that group algebra. A correspondence between inputs and numbers is established. This correspondence is used to prove that the polynomials in the algebra can represent a solution to any pattern recognition problem. When the coefficients of the polynomial are suitably chosen vectors, the natural topology of the input vector space is preserved. The importance of this approach as a basis for a completely general efficient parallel process, and practically realizable pattern recognizing machine is presented. The concept may be realized by a modular parallel process type of machinery.

Original languageEnglish (US)
Pages (from-to)528-530
Number of pages3
JournalIEEE Transactions on Computers
VolumeC-23
Issue number5
StatePublished - May 1974
Externally publishedYes

Fingerprint

Convolution
Algebra
Pattern Recognition
Pattern recognition
Polynomials
Group Algebra
Vector spaces
Polynomial
Vector space
Correspondence
Topological Algebra
Topological group
Machinery
Topology
Coefficient

ASJC Scopus subject areas

  • Hardware and Architecture
  • Electrical and Electronic Engineering

Cite this

PATTERN RECOGNITION BY CONVOLUTION POLYNOMIAL. / Remler, Michael P.

In: IEEE Transactions on Computers, Vol. C-23, No. 5, 05.1974, p. 528-530.

Research output: Contribution to journalArticle

Remler, MP 1974, 'PATTERN RECOGNITION BY CONVOLUTION POLYNOMIAL.', IEEE Transactions on Computers, vol. C-23, no. 5, pp. 528-530.
Remler, Michael P. / PATTERN RECOGNITION BY CONVOLUTION POLYNOMIAL. In: IEEE Transactions on Computers. 1974 ; Vol. C-23, No. 5. pp. 528-530.
@article{c2586a047d8a497bb8c15f0f281509ff,
title = "PATTERN RECOGNITION BY CONVOLUTION POLYNOMIAL.",
abstract = "Pattern recognition is considered as a mapping from the set of all inputs to the numbers 0 to 1. The inputs are treated as vectors. A topological group algebra over the vector space is described. The input is treated as a variable in a polynomial of that group algebra. A correspondence between inputs and numbers is established. This correspondence is used to prove that the polynomials in the algebra can represent a solution to any pattern recognition problem. When the coefficients of the polynomial are suitably chosen vectors, the natural topology of the input vector space is preserved. The importance of this approach as a basis for a completely general efficient parallel process, and practically realizable pattern recognizing machine is presented. The concept may be realized by a modular parallel process type of machinery.",
author = "Remler, {Michael P.}",
year = "1974",
month = "5",
language = "English (US)",
volume = "C-23",
pages = "528--530",
journal = "IEEE Transactions on Computers",
issn = "0018-9340",
publisher = "IEEE Computer Society",
number = "5",

}

TY - JOUR

T1 - PATTERN RECOGNITION BY CONVOLUTION POLYNOMIAL.

AU - Remler, Michael P.

PY - 1974/5

Y1 - 1974/5

N2 - Pattern recognition is considered as a mapping from the set of all inputs to the numbers 0 to 1. The inputs are treated as vectors. A topological group algebra over the vector space is described. The input is treated as a variable in a polynomial of that group algebra. A correspondence between inputs and numbers is established. This correspondence is used to prove that the polynomials in the algebra can represent a solution to any pattern recognition problem. When the coefficients of the polynomial are suitably chosen vectors, the natural topology of the input vector space is preserved. The importance of this approach as a basis for a completely general efficient parallel process, and practically realizable pattern recognizing machine is presented. The concept may be realized by a modular parallel process type of machinery.

AB - Pattern recognition is considered as a mapping from the set of all inputs to the numbers 0 to 1. The inputs are treated as vectors. A topological group algebra over the vector space is described. The input is treated as a variable in a polynomial of that group algebra. A correspondence between inputs and numbers is established. This correspondence is used to prove that the polynomials in the algebra can represent a solution to any pattern recognition problem. When the coefficients of the polynomial are suitably chosen vectors, the natural topology of the input vector space is preserved. The importance of this approach as a basis for a completely general efficient parallel process, and practically realizable pattern recognizing machine is presented. The concept may be realized by a modular parallel process type of machinery.

UR - http://www.scopus.com/inward/record.url?scp=0016060724&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0016060724&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0016060724

VL - C-23

SP - 528

EP - 530

JO - IEEE Transactions on Computers

JF - IEEE Transactions on Computers

SN - 0018-9340

IS - 5

ER -