Swarm Based Algorithms for Neural Network Training

被引：0
|
作者：
McLean, Reginald [1 ]
Ombuki-Berman, Beatrice [1 ]
Engelbrecht, Andries P. [2 ,3 ]
机构：
[1] Brock Univ, Dept Comp Sci, St Catharines, ON, Canada
[2] Stellenbosch Univ, Dept Ind Engn, Stellenbosch, South Africa
[3] Stellenbosch Univ, Comp Sci Div, Stellenbosch, South Africa
来源：
2020 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC) | 2020年
关键词：
OPTIMIZATION;
D O I：
10.1109/smc42975.2020.9283242
中图分类号：
TP3 [计算技术、计算机技术];
学科分类号：
0812 ;
摘要：
The purpose of this paper is to compare the abilities and deficiencies of various swarm based algorithms for training artificial neural networks. This paper uses seven algorithms, seven regression problems, sixteen classification problems, and four bounded activation functions to compare algorithms in regards to loss, accuracy, hidden unit saturation, and overfitting. It was found that particle swarm optimization is the top algorithm for regression problems based on loss, firefly algorithm was the top algorithm for classification problems when examining accuracy and loss. The ant colony optimization and artificial bee colony algorithms caused the least amount of hidden unit saturation, with the bacterial foraging optimization algorithm producing the least amount of overfitting.
引用
收藏
页码：2585 / 2592
页数：8
相关论文
共 50 条
  • [1] Comparison of Particle Swarm Optimization and Backpropagation Algorithms for Training Feedforward Neural Network
    Mohammadi, Nasser
    Mirabedini, Seyed Javad
    [J]. JOURNAL OF MATHEMATICS AND COMPUTER SCIENCE-JMCS, 2014, 12 (02): : 113 - 123
  • [2] Comparison of Swarm-based Metaheuristic and Gradient Descent-based Algorithms in Artif icial Neural Network Training
    Eker, Erdal
    Kayri, Murat
    Ekinci, Serdar
    Izci, Davut
    [J]. ADCAIJ-ADVANCES IN DISTRIBUTED COMPUTING AND ARTIFICIAL INTELLIGENCE JOURNAL, 2023, 12 (01):
  • [3] Particle Swarm for Training Cascade Neural Network Based Models/Estimators
    Saranya, V.
    Raghuraman, R.
    Arulselvam, K.
    Thirunavukarasu, K.
    Venkadesan, A.
    [J]. INTERNATIONAL CONFERENCE ON MODELLING OPTIMIZATION AND COMPUTING, 2012, 38 : 2433 - 2452
  • [4] An improved particle swarm optimization based training algorithm for neural network
    Zhao, FQ
    Hong, Y
    Yu, DM
    Yang, YH
    [J]. ICMIT 2005: INFORMATION SYSTEMS AND SIGNAL PROCESSING, 2005, 6041
  • [5] An Improved Particle Swarm Optimization based Neural Network Training for Classification
    Mondal, Palash
    Nandi, Arijit
    Jana, Nanda Dulal
    [J]. PROCEEDINGS OF 2019 IEEE REGION 10 SYMPOSIUM (TENSYMP), 2019, : 681 - 686
  • [6] Grammatical Swarm for Artificial Neural Network Training
    Si, Tapas
    De, Arunava
    Bhattacharjee, Anup Kumar
    [J]. 2014 IEEE INTERNATIONAL CONFERENCE ON CIRCUIT, POWER AND COMPUTING TECHNOLOGIES (ICCPCT-2014), 2014, : 1657 - 1661
  • [7] Parallel algorithms for the training process of a neural network-based system
    Ammar, HH
    Miao, ZH
    [J]. INTERNATIONAL JOURNAL OF HIGH PERFORMANCE COMPUTING APPLICATIONS, 2000, 14 (01): : 3 - 25
  • [8] NEURAL NETWORK TRAINING WITH PARALLEL PARTICLE SWARM OPTIMIZER
    覃征
    刘宇
    王昱
    [J]. Journal of Pharmaceutical Analysis, 2006, (02) : 109 - 112
  • [9] Neural Network Training with Second Order Algorithms
    Yu, H.
    Wilamowski, B. M.
    [J]. HUMAN-COMPUTER SYSTEMS INTERACTION: BACKGROUNDS AND APPLICATIONS 2, PT 2, 2012, 99 : 463 - 476
  • [10] A new ridgelet neural network training algorithm based on improved particle swarm optimization
    Su, Rijian
    Kong, Li
    Song, Shengli
    Zhang, Pu
    Zhou, Kaibo
    Cheng, Jingjing
    [J]. ICNC 2007: THIRD INTERNATIONAL CONFERENCE ON NATURAL COMPUTATION, VOL 3, PROCEEDINGS, 2007, : 411 - +
12345