Autors: Stela Angelova Stefanova.
Title: ONE APPROACH FOR DISCRETE DYNAMICAL SYSTEM MODELING BASED ON FEED-FORWARD NEURAL NETWORK
Keywords: neural networks, optimization, digital filters

Abstract: The approach for discrete dynamical system modeling based on feed-forward neural network is considered. The proposed method is realized in two stages. The first one is training of the feed-forward neural network with given experimental data obtained for the designed system. The second stage is simulation with the neural network model. The variant of the method for feed-forward neural network training known as “backpropagation” is developed. The effective realization in matrix form of the proposed algorithm is given. This approach is successfully applied to the design problem in time dom

References

  1. Bhattacharya D.,Antoniou A., 1996, Real-time Design of FIR Filter by Feedback Neural Network, , May 1996, <>, IEEE
  2. Pedersen M.,, 1997, Optimization of Recurrent Neural Networks for Time Domain Series Modeling, Ph.D., <Technical University of Denmark>
  3. Stefanova S.,, 1994, ELECTRONICS ET’ 2004:Time Domain Recursive Digital Filter Modeling Based on Recurrent Neural Network Training, Sozopol, September 2004, <Sozopol>,
  4. Pei, S.,Hsu, Ch., Wang, P.,, 2002, n Circuits and Systems-II Analog and Digital Signal Processing: Design of a class of IIR eigenfilters with time and frequency domain constraints, , February 2002, <>, IEEE
  5. Jin, L.,Nikiforuk, P.,Gupta, M., 1995, Transactions on Automatic Control: Approximation of Discrete-Time State-Space Trajectories Using Dynamical Recurrent Neural Networks, , 1995, <>, IEEE

Issue

ELECTRONICS’ 2005,21 – 23 September, vol. 1, pp. 101-106, 2005, Bulgaria,

Вид: пленарен доклад в международен форум