Grammatical Swarm for Artificial Neural Network Training

被引：0
|
作者：
Si, Tapas [1 ]
De, Arunava [2 ]
Bhattacharjee, Anup Kumar [3 ]
机构：
[1] Bankura Unnayani Inst Engn, Dept CSE, Bankura, WB, India
[2] Dr BC Roy Engn Coll, Dept IT, Durgapur, W Bengal, India
[3] Natl Inst Technol, Dept ECE, Durgapur, W Bengal, India
来源：
2014 IEEE INTERNATIONAL CONFERENCE ON CIRCUIT, POWER AND COMPUTING TECHNOLOGIES (ICCPCT-2014) | 2014年
关键词：
Artificial neural network; Grammatical evolution; Grammatical swarm; Particle swarm optimizer; Comprehensive learning particle swarm optimizer; Differential evolution; Trigonometric differential evolution; XOR problem; EVOLUTION;
D O I：
暂无
中图分类号：
TP39 [计算机的应用];
学科分类号：
081203 ; 0835 ;
摘要：
This paper presents a proof of concept for Artificial Neural Network training using Grammatical Swarm. Grammatical Swarm is a variant of Grammatical Evolution. The synaptic weight coefficients of a multilayer feed-forward neural network are evolved using Grammatical Swarm. The synaptic weight coefficients are derived from predefined BackusNaur Form grammar for real value generation in a specified range. The proposed method is applied to solve XOR problem and compared with the multilayer feed-forward neural network training using Particle Swarm Optimizer, Comprehensive Learning Particle Swarm Optimizer, Differential Evolution and Trigonometric Differential Evolution. The experimental results shows that Grammatical Swarm is able to train the Artificial Neural Network.
引用
收藏
页码：1657 / 1661
页数：5
相关论文
共 50 条
  • [1] A hybrid of artificial fish swarm algorithm and particle swarm optimization for feedforward neural network training
    Chen, Huadong
    Wang, Shuzong
    Li, Jingxi
    Li, Yunfan
    [J]. PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON INTELLIGENT SYSTEMS AND KNOWLEDGE ENGINEERING (ISKE 2007), 2007,
  • [2] Neural network construction and training using grammatical evolution
    Tsoulos, Ioannis
    Gavrilis, Dimitris
    Glavas, Euripidis
    [J]. NEUROCOMPUTING, 2008, 72 (1-3) : 269 - 277
  • [3] Hardware Implementation of Artificial Neural Network Training Using Particle Swarm Optimization on FPGA
    Cavuslu, Mehmet Ali
    Karakuzu, Cihan
    Sahin, Suhap
    [J]. JOURNAL OF POLYTECHNIC-POLITEKNIK DERGISI, 2010, 13 (02): : 83 - 92
  • [4] Optimized Particle Swarm Optimization (OPSO) and its application to artificial neural network training
    Michael Meissner
    Michael Schmuker
    Gisbert Schneider
    [J]. BMC Bioinformatics, 7
  • [5] Optimized Particle Swarm Optimization (OPSO) and its application to artificial neural network training
    Meissner, Michael
    Schmuker, Michael
    Schneider, Gisbert
    [J]. BMC BIOINFORMATICS, 2006, 7 (1)
  • [6] Swarm Based Algorithms for Neural Network Training
    McLean, Reginald
    Ombuki-Berman, Beatrice
    Engelbrecht, Andries P.
    [J]. 2020 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC), 2020, : 2585 - 2592
  • [7] Grammatical Swarm and Particle Swarm Optimization models applied to Neural Network learning and topology definition
    Gomez, Nuria
    Mingo, Luis F.
    Garitagoitia, Juan
    Martinez, Victor
    Calvo Manzano, Jose A.
    [J]. PROCEEDINGS OF THE 8TH WSEAS INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE, MAN-MACHINE SYSTEMS AND CYBERNETICS (CIMMACS '09), 2009, : 180 - +
  • [8] Training simple recurrent deep artificial neural network for forecasting using particle swarm optimization
    Bas, Eren
    Egrioglu, Erol
    Kolemen, Emine
    [J]. GRANULAR COMPUTING, 2022, 7 (02) : 411 - 420
  • [9] Training simple recurrent deep artificial neural network for forecasting using particle swarm optimization
    Eren Bas
    Erol Egrioglu
    Emine Kolemen
    [J]. Granular Computing, 2022, 7 : 411 - 420
  • [10] An approach to artificial neural network training
    Czarnowski, I
    Jedrzejowicz, P
    [J]. RESEARCH AND DEVELOPMENT IN INTELLIGENT SYSTEM XIX, 2003, : 149 - 162
12345