In this paper, we propose a stochastic dynamic local search (SDLS) method for Multiple-Valued Logic (MVL) learning by introducing stochastic dynamics into the traditional local search method. The proposed learning network maintains some trends of quick descent to either global minimum or a local minimum, and at the same time has some chance of escaping from local minima by permitting temporary error increases during learning. Thus the network may eventually reach the global minimum state or its best approximation with very high probability. Simulation results show that the proposed algorithm has the superior abilities to find the global minimum for the MVL network learning within reasonable number of iterations.
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
Qiping CAO, Shangce GAO, Jianchen ZHANG, Zheng TANG, Haruhiko KIMURA, "A Stochastic Dynamic Local Search Method for Learning Multiple-Valued Logic Networks" in IEICE TRANSACTIONS on Fundamentals,
vol. E90-A, no. 5, pp. 1085-1092, May 2007, doi: 10.1093/ietfec/e90-a.5.1085.
Abstract: In this paper, we propose a stochastic dynamic local search (SDLS) method for Multiple-Valued Logic (MVL) learning by introducing stochastic dynamics into the traditional local search method. The proposed learning network maintains some trends of quick descent to either global minimum or a local minimum, and at the same time has some chance of escaping from local minima by permitting temporary error increases during learning. Thus the network may eventually reach the global minimum state or its best approximation with very high probability. Simulation results show that the proposed algorithm has the superior abilities to find the global minimum for the MVL network learning within reasonable number of iterations.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1093/ietfec/e90-a.5.1085/_p
Copy
@ARTICLE{e90-a_5_1085,
author={Qiping CAO, Shangce GAO, Jianchen ZHANG, Zheng TANG, Haruhiko KIMURA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={A Stochastic Dynamic Local Search Method for Learning Multiple-Valued Logic Networks},
year={2007},
volume={E90-A},
number={5},
pages={1085-1092},
abstract={In this paper, we propose a stochastic dynamic local search (SDLS) method for Multiple-Valued Logic (MVL) learning by introducing stochastic dynamics into the traditional local search method. The proposed learning network maintains some trends of quick descent to either global minimum or a local minimum, and at the same time has some chance of escaping from local minima by permitting temporary error increases during learning. Thus the network may eventually reach the global minimum state or its best approximation with very high probability. Simulation results show that the proposed algorithm has the superior abilities to find the global minimum for the MVL network learning within reasonable number of iterations.},
keywords={},
doi={10.1093/ietfec/e90-a.5.1085},
ISSN={1745-1337},
month={May},}
Copy
TY - JOUR
TI - A Stochastic Dynamic Local Search Method for Learning Multiple-Valued Logic Networks
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1085
EP - 1092
AU - Qiping CAO
AU - Shangce GAO
AU - Jianchen ZHANG
AU - Zheng TANG
AU - Haruhiko KIMURA
PY - 2007
DO - 10.1093/ietfec/e90-a.5.1085
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E90-A
IS - 5
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - May 2007
AB - In this paper, we propose a stochastic dynamic local search (SDLS) method for Multiple-Valued Logic (MVL) learning by introducing stochastic dynamics into the traditional local search method. The proposed learning network maintains some trends of quick descent to either global minimum or a local minimum, and at the same time has some chance of escaping from local minima by permitting temporary error increases during learning. Thus the network may eventually reach the global minimum state or its best approximation with very high probability. Simulation results show that the proposed algorithm has the superior abilities to find the global minimum for the MVL network learning within reasonable number of iterations.
ER -