Gradient methods for the optimization of dynamical systems containing neural networks
- 1 March 1991
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 2 (2) , 252-262
- https://doi.org/10.1109/72.80336
Abstract
An extension of the backpropagation method, termed dynamic backpropagation, which can be applied in a straightforward manner for the optimization of the weights (parameters) of multilayer neural networks is discussed. The method is based on the fact that gradient methods used in linear dynamical systems can be combined with backpropagation methods for neural networks to obtain the gradient of a performance index of nonlinear dynamical systems. The method can be applied to any complex system which can be expressed as the interconnection of linear dynamical systems and multilayer neural networks. To facilitate the practical implementation of the proposed method, emphasis is placed on the diagrammatic representation of the system which generates the gradient of the performance function.Keywords
This publication has 6 references indexed in Scilit:
- Identification and control of dynamical systems using neural networksIEEE Transactions on Neural Networks, 1990
- Backpropagation through time: what it does and how to do itProceedings of the IEEE, 1990
- A Learning Algorithm for Continually Running Fully Recurrent Neural NetworksNeural Computation, 1989
- Optimization of time-varying systemsIEEE Transactions on Automatic Control, 1965
- A new approach to the sensitivity problem in multivariable feedback system designIEEE Transactions on Automatic Control, 1964
- Multiparameter self-optimizing systems using correlation techniquesIEEE Transactions on Automatic Control, 1964