Associative memory for intelligent control

Motonobu Hattori, Masafumi Hagiwara

Research output: Contribution to journalArticle

13 Citations (Scopus)

Abstract

In many industrial applications of softcomputing, intelligent controls are important to accomplish high level tasks. Intelligent controls, however, need specific knowledge for each task. Therefore developing good memory is crucial to store the required knowledge efficiently and robustly. Neural network associative memories are the most suitable for the role because of their flexibility and content addressability. In this paper, first, we describe the basic concept of the neural network associative memories and the conventional learning algorithms. After pointing out some problems of the associative memories, we explain a novel learning algorithm, which is superior to the conventional ones. Finally, we introduce an associative memory suited for the intelligent controls and show the effectiveness by a number of computer simulations.

Original languageEnglish
Pages (from-to)349-374
Number of pages26
JournalMathematics and Computers in Simulation
Volume51
Issue number3-4
Publication statusPublished - 2000 Jan

Fingerprint

Intelligent Control
Associative Memory
Intelligent control
Data storage equipment
Learning Algorithm
Learning algorithms
Neural Networks
Soft Computing
Neural networks
Industrial Application
Computer Simulation
Flexibility
Industrial applications
Computer simulation
Knowledge

Keywords

  • Intelligent controls
  • Multimodule associative memory for many-to-many associations
  • Neural network

ASJC Scopus subject areas

  • Information Systems and Management
  • Control and Systems Engineering
  • Applied Mathematics
  • Computational Mathematics
  • Modelling and Simulation

Cite this

Associative memory for intelligent control. / Hattori, Motonobu; Hagiwara, Masafumi.

In: Mathematics and Computers in Simulation, Vol. 51, No. 3-4, 01.2000, p. 349-374.

Research output: Contribution to journalArticle

@article{00fcff386054413ea335705959be16e7,
title = "Associative memory for intelligent control",
abstract = "In many industrial applications of softcomputing, intelligent controls are important to accomplish high level tasks. Intelligent controls, however, need specific knowledge for each task. Therefore developing good memory is crucial to store the required knowledge efficiently and robustly. Neural network associative memories are the most suitable for the role because of their flexibility and content addressability. In this paper, first, we describe the basic concept of the neural network associative memories and the conventional learning algorithms. After pointing out some problems of the associative memories, we explain a novel learning algorithm, which is superior to the conventional ones. Finally, we introduce an associative memory suited for the intelligent controls and show the effectiveness by a number of computer simulations.",
keywords = "Intelligent controls, Multimodule associative memory for many-to-many associations, Neural network",
author = "Motonobu Hattori and Masafumi Hagiwara",
year = "2000",
month = "1",
language = "English",
volume = "51",
pages = "349--374",
journal = "Mathematics and Computers in Simulation",
issn = "0378-4754",
publisher = "Elsevier",
number = "3-4",

}

TY - JOUR

T1 - Associative memory for intelligent control

AU - Hattori, Motonobu

AU - Hagiwara, Masafumi

PY - 2000/1

Y1 - 2000/1

N2 - In many industrial applications of softcomputing, intelligent controls are important to accomplish high level tasks. Intelligent controls, however, need specific knowledge for each task. Therefore developing good memory is crucial to store the required knowledge efficiently and robustly. Neural network associative memories are the most suitable for the role because of their flexibility and content addressability. In this paper, first, we describe the basic concept of the neural network associative memories and the conventional learning algorithms. After pointing out some problems of the associative memories, we explain a novel learning algorithm, which is superior to the conventional ones. Finally, we introduce an associative memory suited for the intelligent controls and show the effectiveness by a number of computer simulations.

AB - In many industrial applications of softcomputing, intelligent controls are important to accomplish high level tasks. Intelligent controls, however, need specific knowledge for each task. Therefore developing good memory is crucial to store the required knowledge efficiently and robustly. Neural network associative memories are the most suitable for the role because of their flexibility and content addressability. In this paper, first, we describe the basic concept of the neural network associative memories and the conventional learning algorithms. After pointing out some problems of the associative memories, we explain a novel learning algorithm, which is superior to the conventional ones. Finally, we introduce an associative memory suited for the intelligent controls and show the effectiveness by a number of computer simulations.

KW - Intelligent controls

KW - Multimodule associative memory for many-to-many associations

KW - Neural network

UR - http://www.scopus.com/inward/record.url?scp=0041495651&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0041495651&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0041495651

VL - 51

SP - 349

EP - 374

JO - Mathematics and Computers in Simulation

JF - Mathematics and Computers in Simulation

SN - 0378-4754

IS - 3-4

ER -