Abstract
By combining multilayer perceptrons (MLPs) and radial basis function neural networks (RBF-NNs), an efficient multilayer RBF network is proposed in this work for regression problems. As an extension to the existing multilayer RBF network (RBF-MLP-I), the new multilayer RBF network (RBF-MLP-II) first nonlinearly transforms the multi-dimensional input data by adopting a set of multivariate basis functions. Then, linear weighted sums of these basis functions, i.e., the RBF approximations, are computed in the first hidden layer and used as the features of this layer. Subsequently, in the following hidden layers, each feature of the preceding hidden layer is fed into a univariate RBF characterized by the trainable scalar center and width, and then, RBF approximations are also applied to these basis functions. Finally, the features of the last hidden layer are linearly transformed to approximate the target output data. RBF-MLP-II reduces the number of parameters in basis functions and thus the network complexity of RBF-MLP-I. Verified by four regression problems, it is demonstrated that the proposed RBF-MLP-II exhibits the best approximation accuracy and fastest training convergence compared to conventional MLPs, RBF-NNs, and RBF-MLP-I.
Similar content being viewed by others
References
Draper NR, Smith H (1998) Applied regression analysis. John Wiley & Sons, Hoboken
Weisberg S (2005) Applied linear regression. John Wiley & Sons, Hoboken
Bates DM, Watts DG (1988) Nonlinear regression analysis and its applications. Wiley, New York
Montgomery DC, Peck EA, Vining GG (2012) Introduction to linear regression analysis. John Wiley & Sons, Hoboken
Theil H (1992) A rank-invariant method of linear and polynomial regression analysis. Springer, Berlin, pp 345–381
Hosmer DW Jr, Lemeshow S, Sturdivant RX (2013) Applied logistic regression. John Wiley & Sons, Hoboken
Hoerl AE, Kennard RW (1970) Ridge regression: biased estimation for nonorthogonal problems. Technometrics 12:55–67
Tibshirani R (1996) Regression shrinkage and selection via the lasso. J R Stat Soc Ser B 58:267–288
Box GEP, Tiao GC (2011) Bayesian inference in statistical analysis. John Wiley & Sons, Hoboken
Goodfellow I, Bengio Y, Courville A, Bengio Y (2016) Deep learning. MIT Press, Cambridge
Pal SK, Mitra S (1992) Multilayer perceptron, fuzzy sets, and classification. IEEE Trans Neural Netw 3:683–697
LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521:436–444
Gardner MW, Dorling SR (1998) Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences. Atmos Environ 32:2627–2636
Kůrková V (1992) Kolmogorov’s theorem and multilayer neural networks. Neural Netw 5:501–506. https://doi.org/10.1016/0893-6080(92)90012-8
Chen T, Chen H (1995) Universal approximation to nonlinear operators by neural networks with arbitrary activation functions and its application to dynamical systems. IEEE Trans Neural Netw 6:911–917
Chaudhuri BB, Bhattacharya U (2000) Efficient training and improved performance of multilayer perceptron in pattern classification. Neurocomputing 34:11–27
Mazroua AA, Salama MMA, Bartnikas R (1993) PD pattern recognition with neural networks using the multilayer perceptron technique. IEEE Trans Electr Insul 28:1082–1089
Ahmed NK, Atiya AF, El GN, El-Shishiny H (2010) An empirical comparison of machine learning models for time series forecasting. Econom Rev 29:594–621
Koskela T, Lehtokangas M, Saarinen J, Kaski K (1996) Time series prediction with multilayer perceptron, FIR and Elman neural networks. In: Proceedings of the world congress on neural networks. Citeseer, pp 491–496
Shedeed HA, Issa MF, El-Sayed SM (2013) Brain EEG signal processing for controlling a robotic arm. In: Proceedings—2013 8th international conference on computer engineering and systems, ICCES 2013. IEEE, pp 152–157
Nielsen JLG, Holmgaard S, Jiang N et al (2009) Enhanced EMG signal processing for simultaneous and proportional myoelectric control. In: Proceedings of the 31st annual international conference of the IEEE engineering in medicine and biology society: engineering the future of biomedicine, EMBC 2009. IEEE, pp 4335–4338
Sezer OB, Ozbayoglu AM, Dogdu E (2017) An artificial neural network-based stock trading system using technical analysis and big data framework. In: arXiv, pp 223–226
Moon T, Hong S, Choi HY et al (2019) Interpolation of greenhouse environment data using multilayer perceptron. Comput Electron Agric 166:105023
Orr MJL (1996) Introduction to radial basis function networks. University of Edinburgh, Edinburgh, pp 1–67
Broomhead DS, Lowe D (1988) Radial basis functions, multi-variable functional interpolation and adaptive networks
Walczak B, Massart DL (1996) The radial basis functions—partial least squares approach as a flexible non-linear regression technique. Anal Chim Acta 331:177–185
Shu C, Ding H, Yeo KS (2003) Local radial basis function-based differential quadrature method and its application to solve two-dimensional incompressible Navier–Stokes equations. Comput Methods Appl Mech Eng 192:941–954
Shu C, Ding H, Yeo KS (2004) Solution of partial differential equations by a global radial basis function-based differential quadrature method. Eng Anal Bound Elem 28:1217–1226
Ding H, Shu C, Yeo KS, Lu ZL (2005) Simulation of natural convection in eccentric annuli between a square outer cylinder and a circular inner cylinder using local MQ-DQ method. Numer Heat Transf Part A Appl 47:291–313
Harpham C, Dawson CW (2006) The effect of different basis functions on a radial basis function network for time series prediction: a comparative study. Neurocomputing 69:2161–2170
Schwenker F, Kestler HA, Palm G (2001) Three learning phases for radial-basis-function networks. Neural Netw 14:439–458. https://doi.org/10.1016/S0893-6080(01)00027-2
Na S, Xumin L, Yong G (2010) Research on k-means clustering algorithm: an improved k-means clustering algorithm. In: IEEE, pp 63–67
Broomhead DS, Lowe D (1988) Multivariable functional interpolation and adaptive networks, complex systems, vol 2
Chen F-C (1990) Back-propagation neural networks for nonlinear self-tuning adaptive control. IEEE Control Syst Mag 10:44–48
Hecht-Nielsen R (1992) Theory of the backpropagation neural network. Elsevier, New York, pp 65–93
Sibi P, Jones SA, Siddarth P (2013) Analysis of different activation functions using back propagation neural networks. J Theor Appl Inf Technol 47:1264–1268
Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv14126980
Chao J, Hoshino M, Kitamura T, Masuda T (2001) A multilayer RBF network and its supervised learning. In: Proceedings of the international joint conference on neural networks. IEEE, pp 1995–2000
Mhaskar H, Liao Q, Poggio T (2017) When and why are deep networks better than shallow ones? In: Proceedings of the AAAI conference on artificial intelligence
Bottou L (2010) Large-scale machine learning with stochastic gradient descent. In: Proceedings of COMPSTAT’2010. Springer, pp 177–186
Glorot X, Bengio Y (2010) Understanding the difficulty of training deep feedforward neural networks. In: Journal of Machine Learning Research, pp 249–256
Chollet F (2018) Deep Learning mit Python und Keras: Das Praxis-Handbuch vom Entwickler der Keras-Bibliothek. MITP-Verlags GmbH & Co. KG
Abadi M, Agarwal A, Barham P et al (2016) TensorFlow: large-scale machine learning on heterogeneous distributed systems
Jagtap AD, Kawaguchi K, Karniadakis GE (2020) Adaptive activation functions accelerate convergence in deep and physics-informed neural networks. J Comput Phys 404:109136
Jang J-S (1993) ANFIS: adaptive-network-based fuzzy inference system. IEEE Trans Syst Man Cybern 23:665–685
Chen Y, Yang B, Dong J (2006) Time-series prediction using a local linear wavelet neural network. Neurocomputing 69:449–465
De Vito S, Massera E, Piga M et al (2008) On field calibration of an electronic nose for benzene estimation in an urban pollution monitoring scenario. Sens Actuators B Chem 129:750–757
Acknowledgements
This work was partially supported by the research grant of the National University of Singapore (NUS), Ministry of Education. In addition, the first author is thankful to NUS for ring-fenced scholarship.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest to this work.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Jiang, Q., Zhu, L., Shu, C. et al. An efficient multilayer RBF neural network and its application to regression problems. Neural Comput & Applic 34, 4133–4150 (2022). https://doi.org/10.1007/s00521-021-06373-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-021-06373-0