The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Cet article propose un algorithme d'apprentissage de modélisation probabiliste pour l'approche de recherche locale des réseaux logiques à valeurs multiples (MVL). Le modèle d'apprentissage (PMLS) comporte deux phases : une phase de recherche locale (LS) et une phase de modélisation probabiliste (PM). Le LS effectue des recherches en mettant à jour les paramètres du réseau MVL. Cela équivaut à une diminution graduelle des mesures d’erreur et conduit à un minimum d’erreur local qui représente une bonne solution au problème. Une fois que le LS est piégé dans les minima locaux, la phase PM tente de générer un nouveau point de départ pour le LS pour une recherche plus approfondie. On s'attend à ce que la poursuite des recherches soit guidée vers une zone prometteuse par le modèle probabiliste. Ainsi, l’algorithme proposé peut s’échapper des minima locaux et rechercher de meilleurs résultats. Nous testons l'algorithme sur de nombreux réseaux MVL générés aléatoirement. Les résultats de la simulation montrent que l'algorithme proposé est meilleur que les autres méthodes d'apprentissage de recherche locale améliorées, telles que la recherche locale dynamique stochastique (SDLS) et la recherche locale dynamique chaotique (CDLS).
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.
Copier
Shangce GAO, Qiping CAO, Masahiro ISHII, Zheng TANG, "Local Search with Probabilistic Modeling for Learning Multiple-Valued Logic Networks" in IEICE TRANSACTIONS on Fundamentals,
vol. E94-A, no. 2, pp. 795-805, February 2011, doi: 10.1587/transfun.E94.A.795.
Abstract: This paper proposes a probabilistic modeling learning algorithm for the local search approach to the Multiple-Valued Logic (MVL) networks. The learning model (PMLS) has two phases: a local search (LS) phase, and a probabilistic modeling (PM) phase. The LS performs searches by updating the parameters of the MVL network. It is equivalent to a gradient decrease of the error measures, and leads to a local minimum of error that represents a good solution to the problem. Once the LS is trapped in local minima, the PM phase attempts to generate a new starting point for LS for further search. It is expected that the further search is guided to a promising area by the probability model. Thus, the proposed algorithm can escape from local minima and further search better results. We test the algorithm on many randomly generated MVL networks. Simulation results show that the proposed algorithm is better than the other improved local search learning methods, such as stochastic dynamic local search (SDLS) and chaotic dynamic local search (CDLS).
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.E94.A.795/_p
Copier
@ARTICLE{e94-a_2_795,
author={Shangce GAO, Qiping CAO, Masahiro ISHII, Zheng TANG, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Local Search with Probabilistic Modeling for Learning Multiple-Valued Logic Networks},
year={2011},
volume={E94-A},
number={2},
pages={795-805},
abstract={This paper proposes a probabilistic modeling learning algorithm for the local search approach to the Multiple-Valued Logic (MVL) networks. The learning model (PMLS) has two phases: a local search (LS) phase, and a probabilistic modeling (PM) phase. The LS performs searches by updating the parameters of the MVL network. It is equivalent to a gradient decrease of the error measures, and leads to a local minimum of error that represents a good solution to the problem. Once the LS is trapped in local minima, the PM phase attempts to generate a new starting point for LS for further search. It is expected that the further search is guided to a promising area by the probability model. Thus, the proposed algorithm can escape from local minima and further search better results. We test the algorithm on many randomly generated MVL networks. Simulation results show that the proposed algorithm is better than the other improved local search learning methods, such as stochastic dynamic local search (SDLS) and chaotic dynamic local search (CDLS).},
keywords={},
doi={10.1587/transfun.E94.A.795},
ISSN={1745-1337},
month={February},}
Copier
TY - JOUR
TI - Local Search with Probabilistic Modeling for Learning Multiple-Valued Logic Networks
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 795
EP - 805
AU - Shangce GAO
AU - Qiping CAO
AU - Masahiro ISHII
AU - Zheng TANG
PY - 2011
DO - 10.1587/transfun.E94.A.795
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E94-A
IS - 2
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - February 2011
AB - This paper proposes a probabilistic modeling learning algorithm for the local search approach to the Multiple-Valued Logic (MVL) networks. The learning model (PMLS) has two phases: a local search (LS) phase, and a probabilistic modeling (PM) phase. The LS performs searches by updating the parameters of the MVL network. It is equivalent to a gradient decrease of the error measures, and leads to a local minimum of error that represents a good solution to the problem. Once the LS is trapped in local minima, the PM phase attempts to generate a new starting point for LS for further search. It is expected that the further search is guided to a promising area by the probability model. Thus, the proposed algorithm can escape from local minima and further search better results. We test the algorithm on many randomly generated MVL networks. Simulation results show that the proposed algorithm is better than the other improved local search learning methods, such as stochastic dynamic local search (SDLS) and chaotic dynamic local search (CDLS).
ER -