Robust Neural Network Tracking Controller Using Simultaneous Perturbation Stochastic Approximation

  title={Robust Neural Network Tracking Controller Using Simultaneous Perturbation Stochastic Approximation},
  author={Q. Song and J. Spall and Y. Soh and J. Ni},
  journal={IEEE Transactions on Neural Networks},
  • Q. Song, J. Spall, +1 author J. Ni
  • Published 2008
  • Computer Science, Medicine
  • IEEE Transactions on Neural Networks
  • This paper considers the design of robust neural network tracking controllers for nonlinear systems. The neural network is used in the closed-loop system to estimate the nonlinear system function. We introduce the conic sector theory to establish a robust neural control system, with guaranteed boundedness for both the input/output (I/O) signals and the weights of the neural network. The neural network is trained by the simultaneous perturbation stochastic approximation (SPSA) method instead of… CONTINUE READING
    A training algorithm and stability analysis for recurrent neural networks
    • 1
    • PDF
    A robust extended Elman backpropagation algorithm
    • 3


    Publications referenced by this paper.
    Robust backpropagation training algorithm for multilayered neural tracking controller
    • 67
    • Highly Influential
    Discrete-Time Adaptive Backstepping Nonlinear Control via High-Order Neural Networks
    • 128
    Stable neural-network-based adaptive control for sampled-data nonlinear systems
    • 91
    Model-free control of nonlinear stochastic systems with discrete-time measurements
    • 230
    • PDF
    Adaptive control of a class of nonlinear discrete-time systems using neural networks
    • 515
    • PDF