Wavelet Neural Network with Random Wavelet Function Parameters


Department of Computer Engineering, Esfarayen University of Technology, Esfarayen, North Khorasan, Iran


The training algorithm of Wavelet Neural Networks (WNN) is a bottleneck which impacts on the accuracy of the final WNN model. Several methods have been proposed for training the WNNs. From the perspective of our research, most of these algorithms are iterative and need to adjust all the parameters of WNN. This paper proposes a one-step learning method which changes the weights between hidden layer and output layer of the network; meanwhile, the wavelet function parameters are randomly assigned and kept fixed during the training process. Besides the simplicity and speed of the proposed one-step algorithm, the experimental results verify the performance of the proposed method in terms of final model accuracy and computational time.


1.     Bazoobandi, H. and Eftekhari, M., "A differential evolution and spatial distribution based local search for training fuzzy wavelet neural network", International Journal of Engineering-Transactions B: Applications,Vol. 27, No. 8, (2014), 1185-1194.
2.     Bazoobandi, H.-A. and Eftekhari, M., "A fuzzy based memetic algorithm for tuning fuzzy wavelet neural network parameters", Journal of Intelligent & Fuzzy Systems,Vol. 29, No. 1,(2015), 241-252.
3.     Daubechies, I., "Ten lectures on wavelets". SIAM, (1992).
4.     Zhang, Q. and Benveniste, A., "Wavelet networks", IEEE transactions on Neural Networks,Vol. 3, No. 6,(1992), 889-898.
5.     Lin, C.-J., "Wavelet neural networks with a hybrid learning approach", Journal of Information Science and Engineering,Vol. 22, No. 6, (2006), 1367-1387.
6.     Abiyev, R.H. and Kaynak, O., "Fuzzy wavelet neural networks for identification and control of dynamic plants—a novel structure and a comparative study", IEEE Transactions on Industrial Electronics,Vol. 55, No. 8,(2008), 3133-3140.
7.     Ganjefar, S. and Tofighi, M., "Single-hidden-layer fuzzy recurrent wavelet neural network: Applications to function approximation and system identification", Information Sciences,Vol. 294, (2015), 269-285.
8.     Tzeng, S.-T., "Design of fuzzy wavelet neural networks using the GA approach for function approximation and system identification", Fuzzy Sets and Systems,Vol. 161, No. 19, (2010), 2585-2596.
9.     Chen, J. and Bruns, D.D., "WaveARX neural network development for system identification using a systematic design synthesis", Industrial & Engineering Chemistry Research,Vol. 34, No. 12, (1995), 4420-4435.
10.   Yao, S., Wei, C., and He, Z., "Evolving wavelet neural networks for function approximation", Electronics Letters,Vol. 32, No. 4, (1996), 360-369.
11.   Hashemi, S.M.A., Haji Kazemi, H., and Karamodin, A., "Verification of an Evolutionary-based Wavelet Neural Network Model for Nonlinear Function Approximation", International Journal of Engineering-Transactions A: Basics,Vol. 28, No. 10, (2015), 1423-1429.
12.   Cheng, R. and Bai, Y., "A novel approach to fuzzy wavelet neural network modeling and optimization", International Journal of Electrical Power & Energy Systems,Vol. 64, No. (2015), 671-678.
13.   Schmidt, W.F., Kraaijveld, M.A., and Duin. R.P., "Feedforward neural networks with random weights", in Pattern Recognition, Vol. II. Conference B: Pattern Recognition Methodology and Systems, Proceedings., 11th IAPR International Conference on. IEEE, (1992).
14.   Pao, Y.-H. and Takefuji, Y., "Functional-link net computing: theory, system architecture, and functionalities", Computer,Vol. 25, No. 5,(1992), 76-79.
15.   Pao, Y.-H., Park, G.-H., and Sobajic, D.J., "Learning and generalization characteristics of the random vector functional-link net", Neurocomputing,Vol. 6., No. 2,(1994), 163-180.
16.   Igelnik, B. and Pao, Y.-H., "Stochastic choice of basis functions in adaptive function approximation and the functional-link net", IEEE transactions on Neural Networks,Vol. 6, No. 6,(1995), 1320-1329.
17.   Mc Loone, S. and Irwin, G., "Improving neural network training solutions using regularisation", Neurocomputing,Vol. 37, No. 1,(2001), 71-90.
18.   McLoone, S., Brown M.D., Irwin G., Lightbody A., "A hybrid linear/nonlinear training algorithm for feedforward neural networks", IEEE transactions on Neural Networks,Vol. 9, No. 4,(1998), 669-684.
19.   Huang, G.-B., Zhu, Q.-Y., and Siew, C.-K., "Extreme learning machine: theory and applications", Neurocomputing,Vol. 70, No. 1,(2006), 489-501.
20.   Li, M. and Wang, D., "Insights into randomized algorithms for neural networks: Practical issues and common pitfalls", Information Sciences,Vol. 382, (2017), 170-178.
21.   Zhang, L. and Suganthan, P.N., "A survey of randomized algorithms for training neural networks", Information Sciences,Vol. 364, (2016), 146-155.
22.   Zainuddin, Z. and Pauline, O., "Modified wavelet neural network in function approximation and its application in prediction of time-series pollution data", Applied Soft Computing,Vol. 11, No. 8, (2011), 4866-4874.
23.   Samiee, K., Iosifidis A., and Gabbouj, M., "On the comparison of random and Hebbian weights for the training of single-hidden layer feedforward neural networks", Expert Systems with Applications,Vol. 83, No. (2017), 177-186.