Training the multifeedback-layer neural network using the Particle Swarm Optimization algorithm

In this study, the Multifeedback-Layer Neural Network (MFLNN) weights are trained by the Particle Swarm Optimization (PSO). This method (MFLNN-PSO) is applied to two different problems to prove accomplishment of the study. Firstly, a chaotic time series prediction problem is used to test the MFLNN-PSO. Also, the method is used for identification of a non-linear dynamic system. This study shows that the MFLNN-PSO can be used for dynamic system identification as well as controller design.

[1]  Inayet Ozge Aksu,et al.  Identification of disk drive systems using the Multifeedback-Layer Neural Network and the Particle Swarm Optimization algorithm , 2013, 2013 The International Conference on Technological Advances in Electrical, Electronics and Computer Engineering (TAEECE).

[2]  Ramazan Coban.  A context layered locally recurrent neural network for dynamic system identification , 2013, Eng. Appl. Artif. Intell..

[3]  Michael I. Jordan.  Supervised learning and systems with excess degrees of freedom , 1988 .

[4]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[5]  Aydogan Savran,et al.  Multifeedback-Layer Neural Network , 2007, IEEE Transactions on Neural Networks.

[6]  R. Eberhart,et al.  Empirical study of particle swarm optimization , 1999, Proceedings of the 1999 Congress on Evolutionary Computation-CEC99 (Cat. No. 99TH8406).

[7]  P. S. Sastry,et al.  Memory neuron networks for identification and control of dynamical systems , 1994, IEEE Trans. Neural Networks.

[8]  James Kennedy,et al.  Particle swarm optimization , 2002, Proceedings of ICNN'95 - International Conference on Neural Networks.

[9]  Chia-Feng Juang,et al.  A recurrent self-organizing neural fuzzy inference network , 1997, Proceedings of 6th International Fuzzy Systems Conference.