Comparison of four gradient-learning algorithms for neural network Wiener models

From MaRDI portal





The paper deals with gradient-based training algorithms of the neural network model of the Wiener system. The backpropagation, dynamic backpropagation and backpropagation through time learning method are considered, and the partial derivatives (of various kind) used in these training algorithms are computed. Some accuracy questions and computational complexity are discussed in the framework of Wiener system. Efficiency of the resulting neural network Wiener models is illustrated by means of simulation and a real-life process example.











This page was built for publication: Comparison of four gradient-learning algorithms for neural network Wiener models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4827694)