Modified Functional Link Artificial Neural Network
Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 32870
Modified Functional Link Artificial Neural Network

Authors: Ashok Kumar Goel, Suresh Chandra Saxena, Surekha Bhanot

Abstract:

In this work, a Modified Functional Link Artificial Neural Network (M-FLANN) is proposed which is simpler than a Multilayer Perceptron (MLP) and improves upon the universal approximation capability of Functional Link Artificial Neural Network (FLANN). MLP and its variants: Direct Linear Feedthrough Artificial Neural Network (DLFANN), FLANN and M-FLANN have been implemented to model a simulated Water Bath System and a Continually Stirred Tank Heater (CSTH). Their convergence speed and generalization ability have been compared. The networks have been tested for their interpolation and extrapolation capability using noise-free and noisy data. The results show that M-FLANN which is computationally cheap, performs better and has greater generalization ability than other networks considered in the work.

Keywords: DLFANN, FLANN, M-FLANN, MLP

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1061782

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1766

References:


[1] Guez Allon, James L. Ellbert and Moshe Kam, "Neural networks architecture for control," IEEE Control System magazine, pp. 22-25, 1998.
[2] Rivals Isabelle and Léon Personnaz, "Nonlinear internal model control using neural networks: Application to processes with delay and design issues," IEEE Trans. on Neural Networks, vol. 11, no.1, pp. 80-90, 2000.
[3] Yu Wen and Li Xiaoou, "Some new results on system identification with dynamic neural networks," IEEE Transactions on Neural Networks, vol.12, no. 2, pp. 412-417, 2001.
[4] Naira Hovakimyan, Flavio Nardi, Anthony Calise, and Nakwan Kim, "Adaptive output feedback control of uncertain nonlinear systems using single-hidden-layer neural networks," IEEE Trans. on Neural Networks, vol. 13, no. 6, pp. 1420-1431, 2002.
[5] Sunan N Huang., K. K. Tan and T. H. Lee, "Further results on adaptive control for a class of nonlinear systems using neural networks," IEEE Trans. on Neural Networks, vol. 14, no. 3, pp. 719-722, 2003.
[6] Sam Ge Shuzhi and Cong Wang, "Adaptive neural control of uncertain MIMO nonlinear systems," IEEE Trans. on Neural Networks, vol. 15, no. 3, pp. 674-692, 2004.
[7] S. E Lee and B. R. Holt, "Regression analysis of spectroscopic process data using a combined architecture of linear and nonlinear artificial neural networks," Neural Networks, vol. 4, pp. 549-554, 1992.
[8] Ying-Kai Zhao, Ning Cai, "DLF NEural network applied to process modelling and control," Proc. Pacific-Asian Conf. on Expert Systems PACES'95: Huangshan, PR China (1995)
[9] T.X Brown., "A high performance two-stage packet switch architecture," IEEE Transactions on Communications, vol. 47, no. 8, pp. 1792-1795, 1999.
[10] Y. -H. Pao, "Adaptive pattern recognition and neural networks," (Addison-Wesley (1989)
[11] S. Chen and S. A. Billings, "Neural networks for non-linear dynamic system modeling and identification," Int. J. of Control, vol. 56, no. 2, pp. 319-346, 1992.
[12] J. C Patra., R. N. Pal and B. N.Chatterji, "Identification of non-linear dynamic systems using functional link artificial neural networks," IEEE Trans. on Neural Networks, vol. 29, no. 2, pp. 254-262, 1999.
[13] A Ugena., F.de Arriaga and M. El Alami, "Speaker-independent speech recognition by means of functional-link neural networks," Int. Conf. on Pattern Recognition (ICPR'00)-Vol. 2, Barcelona, Spain (2000)
[14] L.H.P Harada.; A.C Da Costa.; R.M Filho., "Hybrid neural modeling of bioprocesses using functional link networks," Applied Biochemistry and Biotechnology, vol. 98, no. 1-3, pp. 1009-1024, 2002.
[15] A. Sierra, J. A. Macias and F. Corbacho, "Evolution of functional link networks," IEEE Trans. on Evolutionary Computation, vol. 5, no. 1, pp 54-65, 2001.
[16] A. K Goel. and S Bhanot, "Modelling of continually stirred tank heater with ANNs using successive over-relaxation backpropagation algorithm," ASCC-02, Proc. of the Asian Control Conf., (Singapore), pp. 614-617, 2002.
[17] A.K. Goel., S. C. Saxena and S. Bhanot, "Fast learning algorithm for training feedforward neural networks," Int. J. of Systems Science, communicated for publication.