Multiplicative neuron model artificial neural network based on Gaussian activation function

被引:41
|
作者
Gundogdu, Ozge [1 ]
Egrioglu, Erol [2 ]
Aladag, Cagdas Hakan [3 ]
Yolcu, Ufuk [4 ]
机构
[1] Cumhuriyet Univ, Dept Econometr, Sivas, Turkey
[2] Marmara Univ, Dept Stat, Istanbul, Turkey
[3] Hacettepe Univ, Dept Stat, Ankara, Turkey
[4] Ankara Univ, Dept Stat, TR-06100 Ankara, Turkey
来源
NEURAL COMPUTING & APPLICATIONS | 2016年 / 27卷 / 04期
关键词
Artificial neural network; Multiplicative neuron model; Gaussian activation function; Forecasting; Particle swarm optimization; FUZZY TIME-SERIES; PREDICTION;
D O I
10.1007/s00521-015-1908-x
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Multiplicative neuron model-based artificial neural networks are one of the artificial neural network types which have been proposed recently and have produced successful forecasting results. Sigmoid activation function was used in multiplicative neuron model-based artificial neural networks in the previous studies. Although artificial neural networks which involve the use of radial basis activation function produce more successful forecasting results, Gaussian activation function has not been used for multiplicative neuron model yet. In this study, rather than using a sigmoid activation function, Gaussian activation function was used in multiplicative neuron model artificial neural network. The weights of artificial neural network and parameters of activation functions were optimized by guaranteed convergence particle swarm optimization. Two major contributions of this study are as follows: the use of Gaussian activation function in multiplicative neuron model for the first time and the optimizing of central and propagation parameters of activation function with the weights of artificial neural network in a single optimization process. The superior forecasting performance of the proposed Gaussian activation function-based multiplicative neuron model artificial neural network was proved by applying it to real-life time series.
引用
收藏
页码:927 / 935
页数:9
相关论文
共 50 条