Solving SAT by Parallel Execution of Neural Networks with Probabilistic Attenuation Coefficient Generator

被引：0
|
作者：
Zhang, Kairong [1 ]
Nagamatu, Masahiro [1 ]
机构：
[1] Kyushu Inst Technol, Grad Sch Life Sci & Syst Engn, Kitakyushu, Fukuoka 804, Japan
来源：
IECON 2004: 30TH ANNUAL CONFERENCE OF IEEE INDUSTRIAL ELECTRONICS SOCIETY, VOL 3 | 2004年
关键词：
D O I：
暂无
中图分类号：
T [工业技术];
学科分类号：
08 ;
摘要：
We have proposed a neural network named LPPH for the SAT. In order to solve the SAT more efficiently, a parallel execution has been proposed. Experimental results show that higher ratio of speedup is obtained by using this parallel execution of the LPPH. There is an important parameter named attenuation coefficient in the dynamics of the LPPH, which affects strongly the speed of execution of the LPPH. In this paper, a method is proposed to generate attenuation coefficients for the dynamics of the LPPH by using probabilistic generating function. The experimental results show that this method is efficient.
引用
收藏
页码：2163 / 2167
页数：5
相关论文
共 26 条
  • [1] Using Attenuation Coefficient Generating Function in Parallel Execution of Neural Networks for Solving SAT
    Zhang, Kairong
    Nagamatu, Masahiro
    JOURNAL OF ADVANCED COMPUTATIONAL INTELLIGENCE AND INTELLIGENT INFORMATICS, 2005, 9 (02) : 121 - 126
  • [2] Solving satisfiability problem by parallel execution of neural networks with biases
    Zhang, KR
    Nagamatu, M
    ARTIFICIAL NEURAL NETWORKS: FORMAL MODELS AND THEIR APPLICATIONS - ICANN 2005, PT 2, PROCEEDINGS, 2005, 3697 : 969 - 974
  • [3] Parallel execution of neural networks with mixed biases for solving satisfiability problem
    Zhang, Kairong
    Nagamatu, Masahiro
    INTERNATIONAL JOURNAL OF INNOVATIVE COMPUTING INFORMATION AND CONTROL, 2005, 1 (04): : 643 - 657
  • [4] An OpenMP-Based Parallel Execution of Neural Networks Specified in NNEF
    Baek, Nakhoon
    Park, Seung-Jong
    ALGORITHMS AND ARCHITECTURES FOR PARALLEL PROCESSING, ICA3PP 2020, PT II, 2020, 12453 : 723 - 726
  • [5] Parallel Execution of Square Approximation Learning Algorithm for MLP Neural Networks
    Antunovic, Mladen
    Filko, Damir
    Hocenski, Zeljko
    2008 MEDITERRANEAN CONFERENCE ON CONTROL AUTOMATION, VOLS 1-4, 2008, : 1348 - 1353
  • [6] Execution Plan Selection for Parallel Queries Using Graph Neural Networks
    Tao, Wenxia
    Niu, Baoning
    Liu, Haonan
    Computer Engineering and Applications, 2023, 59 (13) : 259 - 265
  • [7] Adaptive Parallel Execution of Deep Neural Networks on Heterogeneous Edge Devices
    Zhou, Li
    Samavatian, Mohammad Hossein
    Bacha, Anys
    Majumdar, Saikat
    Teodorescu, Radu
    SEC'19: PROCEEDINGS OF THE 4TH ACM/IEEE SYMPOSIUM ON EDGE COMPUTING, 2019, : 195 - 208
  • [8] Parallel probabilistic self organizing hierarchical neural networks (PPSHNN)
    Valafar, F
    Ersoy, O
    METMBS'00: PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON MATHEMATICS AND ENGINEERING TECHNIQUES IN MEDICINE AND BIOLOGICAL SCIENCES, VOLS I AND II, 2000, : 609 - 614
  • [9] Systolic array for parallel execution of back-propagation artificial neural networks
    Park, KeeHyun
    Jang, Meungsook
    International Journal of Computers and Applications, 1999, 21 (03): : 79 - 83
  • [10] A Hybrid Material Generation Algorithm with Probabilistic Neural Networks for Solving Classification Problems
    Wedyan, Mohammad
    Alshaweesh, Omar
    Ramadan, Enas
    Alturki, Ryan
    Gazzawe, Foziah
    Alghamdi, Mohammed J.
    INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS, 2022, 13 (05) : 260 - 266
123