This paper describes an advanced rule-embedded neural network (RENN+) that has an extended framework for achieving a very tight integration of learning-based neural networks and rule-bases of existing if-then rules. The RENN+ is effective in pattern recognition with ill-posed conditions. It is basically composed of several component RENNs and an output RENN, which are three-layer back-propagation (BP) networks except for the input layer. Each RENN can be pre-organized by embedding the if-then rules through translation of the rules into logic functions in a disjunctive normal form, and can be trainded to acquire adaptive rules as required. A weight-modification-reduced learning algorithm (WMR) capable of standard regularization is used for the post-training to suppress excessive modification of the weights for the embedded rules. To estimate the effectiveness of the proposed RENN+, it was used for pattern recognition in a radar system for detection of buried pipes. This trial showed that a RENN+ with two component RENNs had good recognition capability, whereas a conventional BP network was ineffective.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Mina MARUYAMA, Nobuo TSUDA, Kiyoshi NAKABAYASHI, "A Rule-Embedded Neural-Network and Its Effectiveness in Pattern Recognition with -Posed Conditions" in IEICE TRANSACTIONS on Information,
vol. E78-D, no. 2, pp. 152-162, February 1995, doi: .
Abstract: This paper describes an advanced rule-embedded neural network (RENN+) that has an extended framework for achieving a very tight integration of learning-based neural networks and rule-bases of existing if-then rules. The RENN+ is effective in pattern recognition with ill-posed conditions. It is basically composed of several component RENNs and an output RENN, which are three-layer back-propagation (BP) networks except for the input layer. Each RENN can be pre-organized by embedding the if-then rules through translation of the rules into logic functions in a disjunctive normal form, and can be trainded to acquire adaptive rules as required. A weight-modification-reduced learning algorithm (WMR) capable of standard regularization is used for the post-training to suppress excessive modification of the weights for the embedded rules. To estimate the effectiveness of the proposed RENN+, it was used for pattern recognition in a radar system for detection of buried pipes. This trial showed that a RENN+ with two component RENNs had good recognition capability, whereas a conventional BP network was ineffective.
URL: https://global.ieice.org/en_transactions/information/10.1587/e78-d_2_152/_p
Copy
@ARTICLE{e78-d_2_152,
author={Mina MARUYAMA, Nobuo TSUDA, Kiyoshi NAKABAYASHI, },
journal={IEICE TRANSACTIONS on Information},
title={A Rule-Embedded Neural-Network and Its Effectiveness in Pattern Recognition with -Posed Conditions},
year={1995},
volume={E78-D},
number={2},
pages={152-162},
abstract={This paper describes an advanced rule-embedded neural network (RENN+) that has an extended framework for achieving a very tight integration of learning-based neural networks and rule-bases of existing if-then rules. The RENN+ is effective in pattern recognition with ill-posed conditions. It is basically composed of several component RENNs and an output RENN, which are three-layer back-propagation (BP) networks except for the input layer. Each RENN can be pre-organized by embedding the if-then rules through translation of the rules into logic functions in a disjunctive normal form, and can be trainded to acquire adaptive rules as required. A weight-modification-reduced learning algorithm (WMR) capable of standard regularization is used for the post-training to suppress excessive modification of the weights for the embedded rules. To estimate the effectiveness of the proposed RENN+, it was used for pattern recognition in a radar system for detection of buried pipes. This trial showed that a RENN+ with two component RENNs had good recognition capability, whereas a conventional BP network was ineffective.},
keywords={},
doi={},
ISSN={},
month={February},}
Copy
TY - JOUR
TI - A Rule-Embedded Neural-Network and Its Effectiveness in Pattern Recognition with -Posed Conditions
T2 - IEICE TRANSACTIONS on Information
SP - 152
EP - 162
AU - Mina MARUYAMA
AU - Nobuo TSUDA
AU - Kiyoshi NAKABAYASHI
PY - 1995
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E78-D
IS - 2
JA - IEICE TRANSACTIONS on Information
Y1 - February 1995
AB - This paper describes an advanced rule-embedded neural network (RENN+) that has an extended framework for achieving a very tight integration of learning-based neural networks and rule-bases of existing if-then rules. The RENN+ is effective in pattern recognition with ill-posed conditions. It is basically composed of several component RENNs and an output RENN, which are three-layer back-propagation (BP) networks except for the input layer. Each RENN can be pre-organized by embedding the if-then rules through translation of the rules into logic functions in a disjunctive normal form, and can be trainded to acquire adaptive rules as required. A weight-modification-reduced learning algorithm (WMR) capable of standard regularization is used for the post-training to suppress excessive modification of the weights for the embedded rules. To estimate the effectiveness of the proposed RENN+, it was used for pattern recognition in a radar system for detection of buried pipes. This trial showed that a RENN+ with two component RENNs had good recognition capability, whereas a conventional BP network was ineffective.
ER -