Comparison of four gradient-learning algorithms for neural network Wiener models
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.
- Analysis of gradient descent learning algorithms for multilayer feedforward neural networks
- The convergence of stochastic gradient algorithms applied to learning in neural networks
- A comparative analysis of optimization and generalization properties of two-layer neural network and random feature models under gradient descent dynamics
- Some comparisons between linear approximation and approximation by neural networks
- Neural networks for parameter estimation in intractable models
- Bounds on the complexity of neural‐network models and comparison with linear methods
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)