Comparative Analysis of Methods for Determining Number of Hidden Neurons in Artificial Neural Network

被引：0

作者：

Vujicic, Tijana ^{[1
]}

Matijevic, Tripo ^{[1
]}

Ljucovic, Jelena ^{[1
]}

Balota, Adis ^{[1
]}

Sevarac, Zoran ^{[2
]}

机构：

[1] Univ Mediterranean, Fac Informat Technol, Vaka Durovica Bb, Podgorica 81000, Montenegro

[2] Univ Belgrade, Fac Org Sci, Jove Ilica 154, Belgrade 11000, Serbia

来源：

CENTRAL EUROPEAN CONFERENCE ON INFORMATION AND INTELLIGENT SYSTEMS (CECIIS 2016) | 2016年

关键词：

artificial neural networks; hidden neurons; methods; test error; comparison;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Neurons in an artificial neural network are grouped in three layers: input, output and hidden layer. Determination of an optimal number of neurons in hidden layer is one of the major difficulties in the process of creating artificial neural network topology. The main goal of this paper is to explore and compare existing methods for determining number of hidden neurons. The research is conducted on two separate datasets with different number of input values and different number of training pairs.

引用

页码：219 / 223

页数：5

共 50 条

[21] Determining significance of input neurons for probabilistic neural network by sensitivity analysis procedure
Kowalski, Piotr A.
Kusy, Maciej
COMPUTATIONAL INTELLIGENCE, 2018, 34 (03) : 895 - 916
[22] Optimization analysis of dynamic sample number and hidden layer node number based on BP neural network
Xu, Chunyun
Xu, Chuanfang
Advances in Intelligent Systems and Computing, 2013, 212 : 687 - 695
[23] Selection of number of hidden neurons in neural networks in renewable energy systems
Sheela, K. G.
Deepa, S. N.
JOURNAL OF SCIENTIFIC & INDUSTRIAL RESEARCH, 2014, 73 (10): : 686 - 688
[24] Novel method for estimating the number of hidden neurons of the feedforward neural networks
1600, Shenyang Institute of Computing Technology (24):
[25] Comparative study of methods to obtain the number of hidden neurons of an auto-encoder in a high-dimensionality context
Vega-Gutierrez, Hector R.
Castorena, Carlos
Alejo, Roberto
Granda-Gutierrez, Everardo E.
IEEE LATIN AMERICA TRANSACTIONS, 2020, 18 (12) : 2196 - 2203
[26] Comparative analysis of artificial neural network models: Application in bankruptcy prediction
Charalambous, C
Charitou, A
Kaourou, F
ANNALS OF OPERATIONS RESEARCH, 2000, 99 (1-4) : 403 - 425
[27] A comparative analysis of Artificial Neural Network technologies in intrusion detection systems
University of Engineering and Technology, Taxila, Pakistan
WSEAS Trans. Comput., 2007, 1 (175-180):
[28] Comparative Analysis of Artificial Neural Network Models: Application in Bankruptcy Prediction
Chris Charalambous
Andreas Charitou
Froso Kaourou
Annals of Operations Research, 2000, 99 : 403 - 425
[29] Dynamically deactivating hidden neurons in a multilayer perceptron neural network
Amin, H
Curtis, KM
HayesGill, BR
ICECS 96 - PROCEEDINGS OF THE THIRD IEEE INTERNATIONAL CONFERENCE ON ELECTRONICS, CIRCUITS, AND SYSTEMS, VOLS 1 AND 2, 1996, : 291 - 294
[30] Processing and Analysis on the GPR Image of Dam Hidden Hazard by Means of Artificial Neural Network
Ge, Shuangcheng
Chen, Jun
Zhao, Yonghui
He, Bo
Chen, Yonggen
NEAR-SURFACE GEOPHYSICS AND GEOHAZARDS, 2014, : 707 - 712

← 1 2 3 4 5 →