On the theory of flexible neural networks – Part I: a survey paper

References

• Albertini, F., & Dai Pra, P. (1995). Forward accessibility for recurrent neural networks. IEEE Transactions on Automatic Control, 40(11), 1962–1968.
   Web of Science ®Google Scholar
• Albertini, F., & Sontag, E.D. (1993a). Uniqueness of weights for neural networks. In R.J. Mammone (Ed.), Artificial neural networks for speech and vision (pp. 113–125). London: Chapman and Hall .
   Google Scholar
• Albertini, F., & Sontag, E.D. (1993b). Uniqueness of weights for recurrent nets. Mathematical theory of networks and systems (Vol. 2, pp. 599–602). Regensburg: Akad Verlag .
   Google Scholar
• Albertini, F., & Sontag, E.D. (1994). State observability in recurrent neural networks. Systems & Control Letters, 22, 235–244.
   Web of Science ®Google Scholar
• Bavafa-Toosi, Y. (2000). On multivariable linear output feedback (MEng thesis). Department of Electrical Engineering, K.N. Toosi University of Technology, Tehran.
   Google Scholar
• Bavafa-Toosi, Y. (2006). Decentralized adaptive control of large-scale systems (PhD dissertation). School of Integrated Design Engineering, Keio University, Yokohama.
   Google Scholar
• Bavafa-Toosi, Y., & Ohmori, H. (2005). Flexible neural networks: Some system-theoretic properties and a new class.In Proceedings of the Joint 44th IEEE Conference on Decision and Control & European Control Conference (pp. 2554–2561). Seville, Spain.
   Google Scholar
• Bavafa-Toosi, Y., & Ohmori, H. (2006) Flexible neural network-based associative memories – part I: Behavior. In Proceedings of the 17th Symposium Mathematical Theory of Networks and Systems. Kyoto, Japan.
   Google Scholar
• Bavafa-Toosi, Y. (2016a). On the theory of flexible neural networks – part II: Associative memories. Manuscript submitted for publication.
   Google Scholar
• Bavafa-Toosi, Y. (2016b). A universal decentralized robust full-model-reference adaptive control with non-identical interconnections. Manuscript submitted for publication.
   Google Scholar
• Bavafa-Toosi, Y., Ohmori, H., & Labibi, B. (2005). Failure-tolerant performance stabilization of the generic large-scale system by decentralized linear output feedback. ISA Transactions, 44(4), 501–513.
   PubMed Web of Science ®Google Scholar
• Bavafa-Toosi, Y., Ohmori, H., & Labibi, B. (2006). A generic approach to the design of decentralized linear output-feedback controllers. Systems & Control Letters, 55, 282–292.
   Web of Science ®Google Scholar
• Bevrani, H. (2002). A novel approach for power system load frequency controller design. Proceedings of the 2002 Asia/Pacific IEEE/PES Transmission and Distribution Conference and Exhibition, 1, 184–189.
   Google Scholar
• Bouaziz, S., Dhahri, H., Alimi, A.M., & Abraham, A. (2013). A hybrid learning algorithm for evolving flexible beta basis function neural tree model. Neurocomputing, 117, 107–117.
   Web of Science ®Google Scholar
• Cybenko, G.V. (1989). Approximation by superpositions of a sigmoidal function. Mathematics of Control, Signals, and Systems, 2, 303–314.
   Google Scholar
• Dhharani, S., Rakkiyappan, R., & Cao, J. (2015). ‘New delay dependent stability criteria for switched hopfield neural networks of neutral type with additive time-varying delay component, Neurocomputing, 151(2), 827–834.
   Web of Science ®Google Scholar
• Donnarumma, F., Prevete, R., & Trautteur, G. (2012). Programming in the brain: A neural network theoretical framework. Connection Science, 24(2–3), 71–90.
   Web of Science ®Google Scholar
• Gong, W., Liang, J., & Cao, J. (2015). Matrix measure method for global exponential stability of complex-valued recurrent neural networks with time-varying delays. Neural Networks, 70, 81–89.
   PubMed Web of Science ®Google Scholar
• Hagan, M.T., Demuth, H.B., Beale, M.H., & Jesus, O. De. (2014). Neural network design (2nd ed.). Oklahoma, OK: Martin Hagan.
   Google Scholar
• Hornik, K., Stinchcombe, M., & White, H. (1989). Multilayer feedforward networks are universal approximators. Neural Networks, 2, 359–366.
   Web of Science ®Google Scholar
• Ismailov, V.E. (2015). Approximation by ridge functions and neural networks with a bounded number of neurons. Applicable Analysis: An International Journal, 94(11), 2245–2260.
   Web of Science ®Google Scholar
• Kerr, J.P., & Bartlett, E.B. (1993). High-speed reconstruction of SPECT images with a tailored piecewise neural network. In Proceedings of the 1993 IEEE Symposium. Nuclear Science and Conference on Medical Imaging (pp. 1317–1321). San Fransisco, CA.
   Google Scholar
• Khaki-Sedigh, A., & Bavafa-Toosi, Y. (2001). Design of Static Linear Multivariable Output Feedback Controllers Using Random Optimization Techniques. Journal of Intelligent and Fuzzy Systems,
   Web of Science ®Google Scholar
  10(3–4), 185–195.
   Google Scholar
• Kim, M., Matsunaga, N., & Kawaji, S. (2003). Estimation of cutting torque in drilling system based on flexible neural network. Proceedings of the 2003 International Joint Conference Neural Networks , 1, 642–647.
   Google Scholar
• Koplon, R., & Sontag, E.D. (1997). Using Fourier-Neural recurrent networks to fit sequential input/output data. Neurocomputing, 15, 225–248.
   Web of Science ®Google Scholar
• Kumar, M., & Yadav, N. (2011). Multilayer perceptrons and radial basis function neural network methods for the solution of differential equation: A survey. Computer & Mathematics with Applications, 26(10), 3796–3811.
   Web of Science ®Google Scholar
• Leonard, J.A., Kramer, M.A., & Ungar, L.H. (1992). Using radial basis functions to approximate a function and its error bounds. IEEE Transactions Neural Networks, 3(4), 624–627.
   PubMed Web of Science ®Google Scholar
• Liu, D., Li, C., Li, H., Wang, D., & Ma, H. (2015). ‘Neural network-based decentralized control of continuous-time nonlinear interconnected systems with unknown dynamics. Neurocomputing, 165, 90–98.
   Web of Science ®Google Scholar
• Mulder, W.De, Bethard, S., & Moens, M.-F. (2015). A survey on the application of recurrent neural networks to statistical language modeling. Computer Speech and Language, 30(1), 61–98.
   Web of Science ®Google Scholar
• Nechyba, M.C., & Xu, Y. (1994). Neural network approach to control system identification with variable activation functions. Proceedings of the 1994 IEEE International Symposium Intelligent Control (pp. 358–363). Columbus, OH.
   Google Scholar
• Pan, Y., Zhou, Q., Lu, Q., & Wu, C. (2015). New dissipativity condition of stochastic fuzzy neural networks with discrete and distributed time-varying delays. Neurocomputing, 162(25), 267–272.
   Web of Science ®Google Scholar
• Park, J., & Sandberg, I.W. (1991). Universal approximation using radial-basis-function networks. Neural Computation, 3, 246–257.
   PubMed Web of Science ®Google Scholar
• Sanguineti, M. (2008). Universal approximation by ridge computational models and neural networks: A survey. The Open Applied Mathematics Journal, 2, 31–58.
   Google Scholar
• Sinha, S. (1999). Chaotic dynamics in iterated map neural networks with piecewise linear activation function. Fundamenta Informaticae, 37, 31–50.
   Google Scholar
• Sollazi, M., & Uncini, A. (2004). Regularizing neural networks using flexible multivariate activation function. Neural Networks, 17(2), 247–260.
   PubMed Web of Science ®Google Scholar
• Sontag, E.D. (1990). Remarks on interpolation and recognition using neural nets. In R.P. Lippmann, J.E. Moody, & D.S. Touretzky (Eds.),
   Google Scholar
  Advances in neural information processing systems (vol. 3, pp. 939–945). San Fransisco, CA: Morgan Kaufmann.
   Google Scholar
• Sontag, E.D. (1997). Recurrent neural networks: Some system-theoretic aspects. In M. Karny, K. Warwick, & V. Kurkova (Eds.), Dealing with complexity: A neural network approach (pp. 1–12). London: Springer-Verlag.
   Google Scholar
• Sontag, E.D., & Sussmann, H.J. (1997). Complete controllability of continuous-time recurrent neural networks. Systems & Control Letters, 30, 177–183.
   Web of Science ®Google Scholar
• Sussmann, H.J. (1992). Uniquesness of weights for minimal feedforward nets with a given input-output map. Neural Networks, 5, 589–593.
   Web of Science ®Google Scholar
• Teshnehlab, M., & Watanabe, K. (1999). Intelligent control based on flexible neural networks. Dordrecht: Kluwer Academic Publishers.
   Google Scholar
• Trentelman, H.L., Stoorvogel, A.A., & Hautus, M.L.J. (2001). Control theory for linear systems. New York, NY: Springer-Verlag.
   Google Scholar
• Wang, L., Zhang, J., & Shao, H. (2015). Existence and global stability of a periodic solution for a cellular neural network. Communications in Nonlinear Science and Numerical Simulation, 19(9), 2983–2992.
   Web of Science ®Google Scholar
• Yang, X., Dai, H., & Sun, Y. (2003). SIMO Fourier neural networks research. Proceedings of the 2003 IEEE Conference on Intelligent Transportation Systems, 2, 1606–1609.
   Google Scholar
• Yang, X., Dai, H., Shen, G., & Sun, Y. (2003). Variable structure and variable learning rate Fourier neural networks research. In Proceedings of the 2003 IEEE International Symposium Intelligent Control (pp. 947–952). Houston.
   Google Scholar
• Yazdanpanah, M.J., Semsar, E., & Lucas, C. (2003). Minimization of actuator repositioning in delayed processes using flexible neural networks. Proceedings of the 2003 IEEE Conference on Control Applications, 1, 331–335.
   Google Scholar