Solving Combinatorial Optimization Problems Using the Oscillatory Neural Network

Yoshiaki WATANABE; Keiichi YOSHINO; Tetsuro KAKESHITA

Solving Combinatorial Optimization Problems Using the Oscillatory Neural Network

Yoshiaki WATANABE, Keiichi YOSHINO, Tetsuro KAKESHITA

Full Text Views

0

Share
Cite this

Summary :

The Hopfield neural network for optimization problems often falls into local minima. To escape from the local minima, the neuron unit in the neural network is modified to become an oscillatory unit by adding a simple self-feedback circuit. By combining the oscillatory unit with an energy-value extraction circuit, an oscillatory neural network is constructed. The network can repeatedly extract solutions, and can simultaneously evaluate them. In this paper, the network is applied to four NP-complete problems to demonstrate its generality and efficiency. The network can solve each problem and can obtain better solutions than the original Hopfield neural network and simple algorithms.

Publication: IEICE TRANSACTIONS on Information Vol.E80-D No.1 pp.72-77

Publication Date: 1997/01/25

Publicized

Online ISSN

DOI

Type of Manuscript

Category: Bio-Cybernetics and Neurocomputing

Cite this

Copy

Yoshiaki WATANABE, Keiichi YOSHINO, Tetsuro KAKESHITA, "Solving Combinatorial Optimization Problems Using the Oscillatory Neural Network" in IEICE TRANSACTIONS on Information, vol. E80-D, no. 1, pp. 72-77, January 1997, doi: .
Abstract: The Hopfield neural network for optimization problems often falls into local minima. To escape from the local minima, the neuron unit in the neural network is modified to become an oscillatory unit by adding a simple self-feedback circuit. By combining the oscillatory unit with an energy-value extraction circuit, an oscillatory neural network is constructed. The network can repeatedly extract solutions, and can simultaneously evaluate them. In this paper, the network is applied to four NP-complete problems to demonstrate its generality and efficiency. The network can solve each problem and can obtain better solutions than the original Hopfield neural network and simple algorithms.
URL: https://globals.ieice.org/en_transactions/information/10.1587/e80-d_1_72/_p

Copy

@ARTICLE{e80-d_1_72,
author={Yoshiaki WATANABE, Keiichi YOSHINO, Tetsuro KAKESHITA, },
journal={IEICE TRANSACTIONS on Information},
title={Solving Combinatorial Optimization Problems Using the Oscillatory Neural Network},
year={1997},
volume={E80-D},
number={1},
pages={72-77},
abstract={The Hopfield neural network for optimization problems often falls into local minima. To escape from the local minima, the neuron unit in the neural network is modified to become an oscillatory unit by adding a simple self-feedback circuit. By combining the oscillatory unit with an energy-value extraction circuit, an oscillatory neural network is constructed. The network can repeatedly extract solutions, and can simultaneously evaluate them. In this paper, the network is applied to four NP-complete problems to demonstrate its generality and efficiency. The network can solve each problem and can obtain better solutions than the original Hopfield neural network and simple algorithms.},
keywords={},
doi={},
ISSN={},
month={January},}

Copy

TY - JOUR
TI - Solving Combinatorial Optimization Problems Using the Oscillatory Neural Network
T2 - IEICE TRANSACTIONS on Information
SP - 72
EP - 77
AU - Yoshiaki WATANABE
AU - Keiichi YOSHINO
AU - Tetsuro KAKESHITA
PY - 1997
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E80-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 1997
AB - The Hopfield neural network for optimization problems often falls into local minima. To escape from the local minima, the neuron unit in the neural network is modified to become an oscillatory unit by adding a simple self-feedback circuit. By combining the oscillatory unit with an energy-value extraction circuit, an oscillatory neural network is constructed. The network can repeatedly extract solutions, and can simultaneously evaluate them. In this paper, the network is applied to four NP-complete problems to demonstrate its generality and efficiency. The network can solve each problem and can obtain better solutions than the original Hopfield neural network and simple algorithms.
ER -