The Training Of Multiplicative Neuron Model Based Artificial Neural Networks With Differential Evolution Algorithm For Forecasting

Bas, Eren

doi:10.1515/jaiscr-2016-0001

Abstract

In recent years, artificial neural networks have been commonly used for time series forecasting by researchers from various fields. There are some types of artificial neural networks and feed forward artificial neural networks model is one of them. Although feed forward artificial neural networks gives successful forecasting results they have a basic problem. This problem is architecture selection problem. In order to eliminate this problem, Yadav et al. (2007) proposed multiplicative neuron model artificial neural network. In this study, differential evolution algorithm is proposed for the training of multiplicative neuron model for forecasting. The proposed method is applied to two well-known different real world time series data.

References

[1] W.S. McCulloch, W. Pitts, A logical calculus of the ideas immanent in nervous activity, Bulletin of Mathematical Biophysics, 5, 1943, 115–133.10.1007/BF02478259
Search in Google Scholar
[2] D.E. Rumelhart, G.E. Hinton, R.J. Williams, Learning Represantations by Backpropagating Errors, Nature, 323, 1986, 533-536.10.1038/323533a0
Search in Google Scholar
[3] M. Basu, T.K. Ho, Learning behavior of single neuron classifiers onlinearly separable or nonseparable inputs, In IEEE LICNN’99, 1999.
Search in Google Scholar
[4] R. Labib, New single neuron structure for solving non-linear problems, In IEEE IJCNN’99, 1999, 617–620.
Search in Google Scholar
[5] T.A. Plate, Randomly connected sigma–pi neurons can form associator networks, NETCNS: Network: Computation in Neural Systems, 11, 2000, 321–322.10.1088/0954-898X_11_4_305
Search in Google Scholar
[6] C.N. Zhang, M. Zhao, M. Wang, Logic operations based on single neuron rational model, IEEE Transactions on Neural Networks, 11, 2000, 739–747.10.1109/72.846745
Search in Google Scholar
[7] R.N. Yadav, N. Kumar, P.K. Kalra, J. John, Learning with generalized-mean neuron model. Neurocomputing, 69, 2006, 2026-2032.10.1016/j.neucom.2005.10.006
Search in Google Scholar
[8] M. Shiblee, B. Chandra, P.K. Kalra, Learning of geometric mean neuron model using resilient propagation algorithm, Expert Systems with Applications, 37, 2010, 7449-7455.10.1016/j.eswa.2010.04.018
Search in Google Scholar
[9] C.H. Aladag, E. Egrioglu, U. Yolcu, Forecast combination by using artificial neural networks, Neural Processing Letters, 32 (3), 2010, 269–276.10.1007/s11063-010-9156-7
Search in Google Scholar
[10] G. Zhang, B.E. Patuwo, Y.M. Hu, Forecasting with artificial neural networks: The state of the art. International Journal of Forecasting, 14, 1998, 35-62.10.1016/S0169-2070(97)00044-7
Search in Google Scholar
[11] R. Sharda, Neural networks for the MS/OR analyst: An application bibliography, Interfaces, 24 (2), 1994, 116–130.10.1287/inte.24.2.116
Search in Google Scholar
[12] A.S. Weigend, B.A. Huberman, D.E. Rumelhart, Predict- ing the future: A connectionist approach, International Journal of Neural Systems, 1, 1990, 193–209.10.1142/S0129065790000102
Search in Google Scholar
[13] A.S. Weigend, B.A. Huberman, D.E. Rumelhart, Predict- ing sunspots and exchange rates with connectionist networks. In: Casdagli, M., Eubank, S. (Eds.), Nonlinear Modeling and Forecasting. Addison-Wesley, Redwood City, CA, 1992, 395–432
Search in Google Scholar
[14] M. Cottrell, B. Girard, Y. Girard, M. Mangeas, C. Muller, Neural modeling for time series: a statistical stepwise method for weight elimination, IEEE Transactions on Neural Networks, 6(6), 1995, 1355–1364.10.1109/72.471372
Search in Google Scholar
[15] R.N. Yadav, P.K. Kalra, J. John, Time series prediction with single multiplicative neuron model, Applied Soft Computing, 7, 2007, 1157-1163.10.1016/j.asoc.2006.01.003
Search in Google Scholar
[16] L. Zhao, Y. Yang, PSO-based single multiplicative neuron model for time series prediction, Expert Systems with Applications, 36, 2009, 2805-2812.10.1016/j.eswa.2008.01.061
Search in Google Scholar
[17] C.H. Aladag, E. Egrioglu, U. Yolcu, A.Z. Dalar A new time invariant fuzzy time series forecasting method based on particle swarm optimization, Applied Soft Computing, 12, 2012, 3291-3299.10.1016/j.asoc.2012.05.002
Search in Google Scholar
[18] R. Storn, K. Price, Differential Evolution: A Simple and Efficient Adaptive Scheme for Global Optimization over Continuous Spaces, Technical Report TR-95-012, International Computer Science Institute, Berkeley, 1995.
Search in Google Scholar
[19] G. Zhang, Time series forecasting using a hybrid ARIMA and neural network model, Neurocomputing, 50, 200, 159-175.10.1016/S0925-2312(01)00702-0
Search in Google Scholar
[20] C.H. Aladag, E. Egrioglu, C. Kadilar, Forecasting nonlinear time series with a hybrid methodology, Applied Mathematic Letters, 22, 2009, 1467-1470.10.1016/j.aml.2009.02.006
Search in Google Scholar
[21] U. Yolcu, E. Egrioglu, C.H. Aladag, A new linear & nonlinear artificial neural network model for time series forecasting, Decision Support Systems, 2013, 1340–1347.10.1016/j.dss.2012.12.006
Search in Google Scholar

The Training Of Multiplicative Neuron Model Based Artificial Neural Networks With Differential Evolution Algorithm For Forecasting

Abstract

Paradigm

My account