QRNN: q-Generalized Random Neural Network

被引:15
作者
Stosic, Dusan [1 ]
Stosic, Darko [1 ]
Zanchettin, Cleber [1 ]
Ludermir, Teresa [1 ]
Stosic, Borko [2 ]
机构
[1] Univ Fed Pernambuco, Ctr Informat, BR-50670901 Recife, PE, Brazil
[2] Univ Fed Rural Pernambuco, Dept Estat & Informat, BR-52171900 Recife, PE, Brazil
关键词
Activation functions; q-Gaussian; random neural networks (RNNs); Tsallis statistics;
D O I
10.1109/TNNLS.2015.2513365
中图分类号
TP18 [人工智能理论];
学科分类号
140502 [人工智能];
摘要
Artificial neural networks (ANNs) are widely used in applications with complex decision boundaries. A large number of activation functions have been proposed in the literature to achieve better representations of the observed data. However, only a few works employ Tsallis statistics, which has successfully been applied to various other fields. This paper presents a random neural network (RNN) with q-Gaussian activation functions [ q-generalized RNN (QRNN)] based on Tsallis statistics. The proposed method employs an additional parameter q (called the entropic index) which reflects the degree of nonextensivity. This approach has the flexibility to model complex decision boundaries of different shapes by varying the entropic index. We conduct numerical experiments to analyze the efficiency of QRNN compared with RNNs and several other classical methods. Statistical tests (Wilcoxon and Friedman) are used to validate our results and show that the QRNN performs significantly better than RNNs with different activation functions. In addition, we find that QRNN outperforms many of the compared classical methods, with the exception of support vector machines, in which case it still exhibits a substantial advantage in terms of implementation simplicity and speed.
引用
收藏
页码:383 / 390
页数:8
相关论文
共 26 条
[1]
AYRNA Research Group, 2016, LERAN ART NEUR NETW
[2]
Bishop CM, 1995, Neural Networks for Pattern Recognition
[3]
Broomhead D. S., 1988, Complex Systems, V2, P321
[4]
LIBSVM: A Library for Support Vector Machines [J].
Chang, Chih-Chung ;
Lin, Chih-Jen .
ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY, 2011, 2 (03)
[5]
A rapid supervised learning neural network for function interpolation and approximation [J].
Chen, CLP .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1996, 7 (05) :1220-1230
[6]
Duch W., 2001, 9th European Symposium on Artificial Neural Networks. ESANN'2001. Proceedings, P81
[7]
Duch W., 1999, Neural Computing Surveys, V2
[8]
Fernández-Delgado M, 2014, J MACH LEARN RES, V15, P3133
[9]
Parameter estimation of q-Gaussian Radial Basis Functions Neural Networks with a Hybrid Algorithm for binary classification [J].
Fernandez-Navarro, Francisco ;
Hervas-Martinez, Cesar ;
Gutierrez, Pedro A. ;
Pena-Barragan, Jose M. ;
Lopez-Granados, Francisca .
NEUROCOMPUTING, 2012, 75 (01) :123-134
[10]
MELM-GRBF: A modified version of the extreme learning machine for generalized radial basis function neural networks [J].
Fernandez-Navarro, Francisco ;
Hervas-Martinez, Cesar ;
Sanchez-Monedero, Javier ;
Antonio Gutierrez, Pedro .
NEUROCOMPUTING, 2011, 74 (16) :2502-2510