An evolutionary neural network approach for module orientation problems

Nobuo Funabiki, Junji Kitamichi, Seishi Nishikawa

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

A novel neural network approach called "Evolutionary Neural Network (ENN)" is presented for the module orientation problem. The goal of this NP-complete problem is to minimize the total wire length by flipping circuit modules with respect to their vertical and/or horizontal axes of symmetry. In order to achieve high quality VLSI systems, it is strongly desired to solve the problem as quickly as possible in the design cycle. Based on the concept of the genetic algorithm, the evolutionary initialization scheme on neuron states is introduced so as to provide a high quality solution within a very short time. The performance of ENN is compared with three heuristic algorithms through simulations on 20 examples with up to 500 modules. The results show that ENN can find the best solutions in the shortest time.

Original languageEnglish
Pages (from-to)849-855
Number of pages7
JournalIEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Volume28
Issue number6
DOIs
Publication statusPublished - 1998
Externally publishedYes

Fingerprint

Neural networks
Heuristic algorithms
Neurons
Computational complexity
Genetic algorithms
Wire
Networks (circuits)

Keywords

  • Evolutionary initialization scheme
  • Module orientation
  • Neural network
  • NP-complete
  • VLSI design

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Artificial Intelligence
  • Human-Computer Interaction

Cite this

An evolutionary neural network approach for module orientation problems. / Funabiki, Nobuo; Kitamichi, Junji; Nishikawa, Seishi.

In: IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, Vol. 28, No. 6, 1998, p. 849-855.

Research output: Contribution to journalArticle

@article{a30d0dea25644c84ab4a264bb0ed8d06,
title = "An evolutionary neural network approach for module orientation problems",
abstract = "A novel neural network approach called {"}Evolutionary Neural Network (ENN){"} is presented for the module orientation problem. The goal of this NP-complete problem is to minimize the total wire length by flipping circuit modules with respect to their vertical and/or horizontal axes of symmetry. In order to achieve high quality VLSI systems, it is strongly desired to solve the problem as quickly as possible in the design cycle. Based on the concept of the genetic algorithm, the evolutionary initialization scheme on neuron states is introduced so as to provide a high quality solution within a very short time. The performance of ENN is compared with three heuristic algorithms through simulations on 20 examples with up to 500 modules. The results show that ENN can find the best solutions in the shortest time.",
keywords = "Evolutionary initialization scheme, Module orientation, Neural network, NP-complete, VLSI design",
author = "Nobuo Funabiki and Junji Kitamichi and Seishi Nishikawa",
year = "1998",
doi = "10.1109/3477.735394",
language = "English",
volume = "28",
pages = "849--855",
journal = "IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics",
issn = "1083-4419",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "6",

}

TY - JOUR

T1 - An evolutionary neural network approach for module orientation problems

AU - Funabiki, Nobuo

AU - Kitamichi, Junji

AU - Nishikawa, Seishi

PY - 1998

Y1 - 1998

N2 - A novel neural network approach called "Evolutionary Neural Network (ENN)" is presented for the module orientation problem. The goal of this NP-complete problem is to minimize the total wire length by flipping circuit modules with respect to their vertical and/or horizontal axes of symmetry. In order to achieve high quality VLSI systems, it is strongly desired to solve the problem as quickly as possible in the design cycle. Based on the concept of the genetic algorithm, the evolutionary initialization scheme on neuron states is introduced so as to provide a high quality solution within a very short time. The performance of ENN is compared with three heuristic algorithms through simulations on 20 examples with up to 500 modules. The results show that ENN can find the best solutions in the shortest time.

AB - A novel neural network approach called "Evolutionary Neural Network (ENN)" is presented for the module orientation problem. The goal of this NP-complete problem is to minimize the total wire length by flipping circuit modules with respect to their vertical and/or horizontal axes of symmetry. In order to achieve high quality VLSI systems, it is strongly desired to solve the problem as quickly as possible in the design cycle. Based on the concept of the genetic algorithm, the evolutionary initialization scheme on neuron states is introduced so as to provide a high quality solution within a very short time. The performance of ENN is compared with three heuristic algorithms through simulations on 20 examples with up to 500 modules. The results show that ENN can find the best solutions in the shortest time.

KW - Evolutionary initialization scheme

KW - Module orientation

KW - Neural network

KW - NP-complete

KW - VLSI design

UR - http://www.scopus.com/inward/record.url?scp=0032293957&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032293957&partnerID=8YFLogxK

U2 - 10.1109/3477.735394

DO - 10.1109/3477.735394

M3 - Article

VL - 28

SP - 849

EP - 855

JO - IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

JF - IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

SN - 1083-4419

IS - 6

ER -