ANALOG CIRCUIT DESIGN BASED ON NEURAL NETWORKS.

Yong B. Cho, Yoshiyasu Takefuji

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

1 Citation (Scopus)

Abstract

Neural networks have been studied for many years with the hope of achieving human-like performance in such fields as speech and image recognition. A recent resurgence has resulted from VLSI advances, neural network models, and learning algorithms. Neural networks are also very suitable in certain areas such as NP-complete constraint and satisfaction problems, due to the nature of parallel and distributed processing. Neural network models are composed of a mass of fairly simple computational elements and rich interconnections between the elements. Neural networks operate in a parallel and distributed fashion which may resemble biological neural networks. Behaviors of neurons and the strengths of synaptic interconnections are simulated by operational amplifiers and resistors respectively. Several examples are presented, including how to build neural network components based on analog circuits for simulating neural networks and conventional logic circuits.

Original languageEnglish
Title of host publicationProceedings of the Annual Southeastern Symposium on System Theory
PublisherIEEE
Pages100-105
Number of pages6
ISBN (Print)0818608471
Publication statusPublished - 1988
Externally publishedYes

Fingerprint

Analog circuits
Neural networks
Network components
Image recognition
Operational amplifiers
Logic circuits
Speech recognition
Resistors
Learning algorithms
Neurons
Processing

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Industrial and Manufacturing Engineering

Cite this

Cho, Y. B., & Takefuji, Y. (1988). ANALOG CIRCUIT DESIGN BASED ON NEURAL NETWORKS. In Proceedings of the Annual Southeastern Symposium on System Theory (pp. 100-105). IEEE.

ANALOG CIRCUIT DESIGN BASED ON NEURAL NETWORKS. / Cho, Yong B.; Takefuji, Yoshiyasu.

Proceedings of the Annual Southeastern Symposium on System Theory. IEEE, 1988. p. 100-105.

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

Cho, YB & Takefuji, Y 1988, ANALOG CIRCUIT DESIGN BASED ON NEURAL NETWORKS. in Proceedings of the Annual Southeastern Symposium on System Theory. IEEE, pp. 100-105.
Cho YB, Takefuji Y. ANALOG CIRCUIT DESIGN BASED ON NEURAL NETWORKS. In Proceedings of the Annual Southeastern Symposium on System Theory. IEEE. 1988. p. 100-105
Cho, Yong B. ; Takefuji, Yoshiyasu. / ANALOG CIRCUIT DESIGN BASED ON NEURAL NETWORKS. Proceedings of the Annual Southeastern Symposium on System Theory. IEEE, 1988. pp. 100-105
@inproceedings{53dfff8ed6e649049164e430a8c88da2,
title = "ANALOG CIRCUIT DESIGN BASED ON NEURAL NETWORKS.",
abstract = "Neural networks have been studied for many years with the hope of achieving human-like performance in such fields as speech and image recognition. A recent resurgence has resulted from VLSI advances, neural network models, and learning algorithms. Neural networks are also very suitable in certain areas such as NP-complete constraint and satisfaction problems, due to the nature of parallel and distributed processing. Neural network models are composed of a mass of fairly simple computational elements and rich interconnections between the elements. Neural networks operate in a parallel and distributed fashion which may resemble biological neural networks. Behaviors of neurons and the strengths of synaptic interconnections are simulated by operational amplifiers and resistors respectively. Several examples are presented, including how to build neural network components based on analog circuits for simulating neural networks and conventional logic circuits.",
author = "Cho, {Yong B.} and Yoshiyasu Takefuji",
year = "1988",
language = "English",
isbn = "0818608471",
pages = "100--105",
booktitle = "Proceedings of the Annual Southeastern Symposium on System Theory",
publisher = "IEEE",

}

TY - GEN

T1 - ANALOG CIRCUIT DESIGN BASED ON NEURAL NETWORKS.

AU - Cho, Yong B.

AU - Takefuji, Yoshiyasu

PY - 1988

Y1 - 1988

N2 - Neural networks have been studied for many years with the hope of achieving human-like performance in such fields as speech and image recognition. A recent resurgence has resulted from VLSI advances, neural network models, and learning algorithms. Neural networks are also very suitable in certain areas such as NP-complete constraint and satisfaction problems, due to the nature of parallel and distributed processing. Neural network models are composed of a mass of fairly simple computational elements and rich interconnections between the elements. Neural networks operate in a parallel and distributed fashion which may resemble biological neural networks. Behaviors of neurons and the strengths of synaptic interconnections are simulated by operational amplifiers and resistors respectively. Several examples are presented, including how to build neural network components based on analog circuits for simulating neural networks and conventional logic circuits.

AB - Neural networks have been studied for many years with the hope of achieving human-like performance in such fields as speech and image recognition. A recent resurgence has resulted from VLSI advances, neural network models, and learning algorithms. Neural networks are also very suitable in certain areas such as NP-complete constraint and satisfaction problems, due to the nature of parallel and distributed processing. Neural network models are composed of a mass of fairly simple computational elements and rich interconnections between the elements. Neural networks operate in a parallel and distributed fashion which may resemble biological neural networks. Behaviors of neurons and the strengths of synaptic interconnections are simulated by operational amplifiers and resistors respectively. Several examples are presented, including how to build neural network components based on analog circuits for simulating neural networks and conventional logic circuits.

UR - http://www.scopus.com/inward/record.url?scp=0023868930&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0023868930&partnerID=8YFLogxK

M3 - Conference contribution

SN - 0818608471

SP - 100

EP - 105

BT - Proceedings of the Annual Southeastern Symposium on System Theory

PB - IEEE

ER -