This work reports on a novel technique that makes use of memory artificial neural network architecture that can learn and transform so as to emulate any non-linear input-output map for multi-input-multi-output systems when no prior knowledge on specific system features exists.
📌 3 Key Takeaways
🎯
Objective & Hypothesis:Currently, almost all efforts for using artificial neural networks for control oriented process identification are based on feed-forward networks.
📊
Key Findings & Data:Provided the system order or the upper limit of the order is known, a neural network design is feasible for which all the collection of previous values of the inputs and outputs of the system to be identified can be used as input data to train in the network computing structures to learn the input-output map.
💡
Conclusion & Impact:This work reports on a novel technique that makes use of memory artificial neural network architecture that can learn and transform so as to emulate any non-linear input-output map for multi-input-multi-output systems when no prior knowledge on specific system features exists.
🔬Design:Research Article
📍Scope:Comprehensive Sample
⚙️Variables:Domain Parameters
Abstract
Currently, almost all efforts for using artificial neural networks for control oriented process identification are based on feed-forward networks. Provided the system order or the upper limit of the order is known, a neural network design is feasible for which all the collection of previous values of the inputs and outputs of the system to be identified can be used as input data to train in the network computing structures to learn the input-output map. This work reports on a novel technique that makes use of memory artificial neural network architecture that can learn and transform so as to emulate any non-linear input-output map for multi-input-multi-output systems when no prior knowledge on specific system features exists.
🔖
Cite This Article
DIMIROVSKI, G. M., ANDREESKI, C. J. (2022). A memory ann computing structure for nonlinear systems emulation identification. Istanbul University Journal of Electrical and Electronics Engineering, Cilt: 3 - Sayı: 2, 905–915. https://ajindex.com/articles/543922
F. Albertini and E. D. Sontag, “For neural networks, function determines form.” Neural Networks, vol. 6, pp. 975-990, 1992
C.J. Andreeski, C.J. and G.M. Dimirovski, Theory, Design and Implementation of Memory ANN Based Computational Technique for Identification of MIMO Non-linear Dynamical Processes, ASE-FEE Technical Research Rep. NNSID-03/ASE00. Skopje, MK: SS Cyril & Methodius University, 2000
V. I. Arnold, “Some questions of approximation and representation of functions.” In: Proceedings of the International Congress of Mathematicians, pp. 339-348. (Translation in English: American Mathematical Society Translations, Vol. 53). Moscow, RUS: MEI Press, 1958
K.J. Aström, P. Albertos, M. Blanke, A. Isidori, W. Schaufelberger, and R. Sanz, Eds., Control of Complex Systems. London, UK: Springer-Verlag, 2001
C. Bishop, Neural Networks for Pattern Recognition. Oxford, UK: Clarendon, 1995
S. Chen, C. F. N. Cowan, and P. M. Grant, ”Orthogonal least squares learning algorithm for radial basis function networks.” IEEE Trans. Neural Networks, vol. 2, no. 2, pp. 302-309, 1991
T. Chen and H. Chen, “Approximation of continuous functionals by neural networks with applications to dynamic systems.” IEEE Trans. Neural Networks, vol. 4, no. 3, pp. 910-918, 1993
G. M. Dimirovski, I.I. Ivanoska, M.J. Stankovski, R.A. Pessu, A. Zakeri and N.E. Gough. “Life-like systems: ANN emulation modelling in intelligent control systems.” In: Proceedings of the 3rd APCA Intl. Conf. on Automatic Control, A. Dourado et al., Eds., vol. 1, pp. 169-176. Coimbra, PT: Assoc. Portuguesa de Controlo Automatico and University of Coimbra, 1998
S. Haykin, Neural Networks: A Comprehensive Foundation (2nd ed.). New York, NY: Macmillan, 1999
H. Katsuura and D. A. Sprecher, “Computational aspects of Kolmogorov’s theorem.” Neural Networks, vol. 7, pp. 455-461, 1994
S. Mcloone and G. W. Irwin, “Fast parallel of-line training of multilayer perceptrons.” IEEE Trans. Neural Networks, vol. 8, no. 3, pp. 646-653, 1997
W. T. Miller, R. S. Sutton, and P. J. Werbos, Neural Networks for Control. Cambrdige, MA: MIT Press, 1992
K. S. Narendra and K. Parthasarathy, “Identification and control using of dynamical systems neural networks.” IEEE Trans. Neural Networks, vol. NN-1, no. 1, pp. 4-27, 1990
D. T. Pham and L. Xing, Neural Networks for Identification, Prediction and Control. London, UK: Springer-Verlag, 1997