SIMPLE 'NEURAL' OPTIMIZATION NETWORKS: AN A/D CONVERTER, SIGNAL DECISION CIRCUIT, AND A LINEAR PROGRAMMING CIRCUIT.

David W. Tank; John J. Hopfield

doi:10.1109/tcs.1986.1085953

SIMPLE 'NEURAL' OPTIMIZATION NETWORKS: AN A/D CONVERTER, SIGNAL DECISION CIRCUIT, AND A LINEAR PROGRAMMING CIRCUIT.

David W. Tank, John J. Hopfield

Research output: Contribution to journal › Article › peer-review

1497 Scopus citations

Abstract

The rapid solution of several optimization problems by highly interconnected networks of simple analog processors is described. Analog-to-digital (A/D) conversion was considered as a simple optimization problem, and an A/D converter of novel architecture was designed. A/D conversion is a simple example of a more general class of signal-decision problems which, as is shown here, can also be solved by appropriately constructed networks. Circuits to solve these problems were designed using general principles which result from an understanding of the basic collective computational properties of a specific class of analog-processor networks. It is also shown that a network which solves linear programming problems can be understood from the same concepts.

Original language	English (US)
Pages (from-to)	533-541
Number of pages	9
Journal	IEEE transactions on circuits and systems
Volume	CAS-33
Issue number	5
DOIs	https://doi.org/10.1109/tcs.1986.1085953
State	Published - 1986
Externally published	Yes

All Science Journal Classification (ASJC) codes

Engineering(all)

Access to Document

10.1109/tcs.1986.1085953

Fingerprint Dive into the research topics of 'SIMPLE 'NEURAL' OPTIMIZATION NETWORKS: AN A/D CONVERTER, SIGNAL DECISION CIRCUIT, AND A LINEAR PROGRAMMING CIRCUIT.'. Together they form a unique fingerprint.

Cite this

@article{582b2d99cb0a49d8b532329c82766841,

title = "SIMPLE 'NEURAL' OPTIMIZATION NETWORKS: AN A/D CONVERTER, SIGNAL DECISION CIRCUIT, AND A LINEAR PROGRAMMING CIRCUIT.",

abstract = "The rapid solution of several optimization problems by highly interconnected networks of simple analog processors is described. Analog-to-digital (A/D) conversion was considered as a simple optimization problem, and an A/D converter of novel architecture was designed. A/D conversion is a simple example of a more general class of signal-decision problems which, as is shown here, can also be solved by appropriately constructed networks. Circuits to solve these problems were designed using general principles which result from an understanding of the basic collective computational properties of a specific class of analog-processor networks. It is also shown that a network which solves linear programming problems can be understood from the same concepts.",

author = "Tank, {David W.} and Hopfield, {John J.}",

year = "1986",

doi = "10.1109/tcs.1986.1085953",

language = "English (US)",

volume = "CAS-33",

pages = "533--541",

journal = "IEEE Transactions on Circuits and Systems",

issn = "0098-4094",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "5",

}

TY - JOUR

T1 - SIMPLE 'NEURAL' OPTIMIZATION NETWORKS

T2 - AN A/D CONVERTER, SIGNAL DECISION CIRCUIT, AND A LINEAR PROGRAMMING CIRCUIT.

AU - Tank, David W.

AU - Hopfield, John J.

PY - 1986

Y1 - 1986

N2 - The rapid solution of several optimization problems by highly interconnected networks of simple analog processors is described. Analog-to-digital (A/D) conversion was considered as a simple optimization problem, and an A/D converter of novel architecture was designed. A/D conversion is a simple example of a more general class of signal-decision problems which, as is shown here, can also be solved by appropriately constructed networks. Circuits to solve these problems were designed using general principles which result from an understanding of the basic collective computational properties of a specific class of analog-processor networks. It is also shown that a network which solves linear programming problems can be understood from the same concepts.

AB - The rapid solution of several optimization problems by highly interconnected networks of simple analog processors is described. Analog-to-digital (A/D) conversion was considered as a simple optimization problem, and an A/D converter of novel architecture was designed. A/D conversion is a simple example of a more general class of signal-decision problems which, as is shown here, can also be solved by appropriately constructed networks. Circuits to solve these problems were designed using general principles which result from an understanding of the basic collective computational properties of a specific class of analog-processor networks. It is also shown that a network which solves linear programming problems can be understood from the same concepts.

UR - http://www.scopus.com/inward/record.url?scp=0022721216&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0022721216&partnerID=8YFLogxK

U2 - 10.1109/tcs.1986.1085953

DO - 10.1109/tcs.1986.1085953

M3 - Article

AN - SCOPUS:0022721216

VL - CAS-33

SP - 533

EP - 541

JO - IEEE Transactions on Circuits and Systems

JF - IEEE Transactions on Circuits and Systems

SN - 0098-4094

IS - 5

ER -

SIMPLE 'NEURAL' OPTIMIZATION NETWORKS: AN A/D CONVERTER, SIGNAL DECISION CIRCUIT, AND A LINEAR PROGRAMMING CIRCUIT.

Abstract

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Cite this