Learning Capabilities of ELM-Trained Time-Varying Neural Networks
System identification in nonstationary environments surely represents a challenging problem. The authors have recently proposed an innovative neural architecture, namely Time-Varying Neural Network (TV-NN), which has shown remarkable identification capabilities in this kind of scenarios. It is characterized by time-varying weights, each being a linear combination of a certain set of basis functions. This inevitably increases the network complexity with respect to the stationary NN counterpart and in order to keep the training time low, an Extreme Learning Machine (ELM) approach has been proposed by the same authors for TV-NN learning, instead of Back-Propagation based techniques. However the learning capabilities of TV-NN trained by means of ELM have not been investigated in the literature and in this contribution such a lack is faced: the theoretical foundations of ELM usage for TV-NN are analytically discussed, by extending the corresponding results obtained in the stationary case study.
KeywordsExtreme Learning Machine Time-Varying Neural Networks Nonstationary System Identification
Unable to display preview. Download preview PDF.
- 1.Cingolani, C., Squartini, S., Piazza, F.: An extreme learning machine approach for training Time Variant Neural Networks. In: Proc. IEEE Asia Pacific Conference on Circuits and Systems, APCCAS 2008, pp. 384–387 (2008)Google Scholar
- 2.Ding, S., Zhao, H., Zhang, Y., Xu, X., Nie, R.: Extreme learning machine: algorithm, theory and applications. Artificial Intelligence Review, 1–13 (2013)Google Scholar
- 4.Horn, R., Johnson, C.: Topics in matrix analysis. Cambridge University Press (1994)Google Scholar
- 6.Huang, G., Wang, D., Lan, Y.: Extreme learning machines: a survey. International Journal of Machine Learning and Cybernetics, 1–16 (2011)Google Scholar
- 11.Ma, W., Hsieh, T., Chi, C.: Doa estimation of quasi-stationary signals via khatri-rao subspace. In: IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2009, pp. 2165–2168 (2009)Google Scholar
- 13.Titti, A., Squartini, S., Piazza, F.: A new time-variant neural based approach for nonstationary and non-linear system identification. In: Proc. IEEE International Symposium on Circuits and Systems, ISCAS 2005, pp. 5134–5137 (2005)Google Scholar
- 15.Ye, Y., Squartini, S., Piazza, F.: A Group Selection Evolutionary Extreme Learning Machine Approach for Time-Variant Neural Networks. In: Neural Nets WIRN10: Proceedings of the 20th Italian Workshop on Neural Nets, pp. 22–33. IOS Press (2011)Google Scholar