Neural net algorithms for dynamical systems

Yiu‐ming CheungNottingham 1992

Abstract

A neural net based algorithm is devised as an alternative to traditional analogue/numerical integration. The new algorithm consists of a multilayered neural net integrator model inspired by the neuron organisation of the vertebrate retina. A mixture of implicit weight setting, supervised and unsupervised learning is employed. The convergence of this approach proves to be fast when compared to existing models producing comparable results.
\n 
\nWhen the model is operating in a closed loop system it yields a consistent estimate of the derivatives of pictorial input profiles.
\n 
\nThe mapping of the resulting neural net models onto single and multiprocessor systems is examined. A general framework is formulated to permit arbitrary network, definition and easy alterations of network parameters.
\n 
\nA parallel processing technique for distributed memory multiprocessor systems is devised. The parallel algorithm yields a large reduction in processing time.
BibTeX
@inproceedings{cheung1992neural,
  author = {Yiu‐ming Cheung},
  title = {{Neural net algorithms for dynamical systems}},
  booktitle = {Nottingham},
  year = {1992},
}

Loading related content...

Figure