Neural network architecture for adaptive system modeling and control
- 1 January 1989
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
A computing architecture for adaptive control and system modeling based on computational features of nonlinear discrete neural networks is proposed. These features are massively parallel and distributed structures for signal processing, with the potential for ever-improving performance through dynamical learning. The proposed delayed-input delayed-state network architecture and the general training scheme are described. A solution for the problem of analog signal representation by a binary neural network is suggested. Illustrative simulation results are promising and show good and robust performance in various cases.Keywords
This publication has 9 references indexed in Scilit:
- A recurrent neural network: Limitations and trainingNeural Networks, 1990
- Hierarchical neural network model for voluntary movement with application to roboticsIEEE Control Systems Magazine, 1988
- A multilayered neural network controllerIEEE Control Systems Magazine, 1988
- Neural nets for adaptive filtering and adaptive pattern recognitionComputer, 1988
- A learning architecture for control based on back-propagation neural networksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1988
- An introduction to computing with neural netsIEEE ASSP Magazine, 1987
- Parameter and Signal Adaptation in the Stretch Reflex LoopPublished by Elsevier ,1976
- A new look at the statistical model identificationIEEE Transactions on Automatic Control, 1974
- Muscle spindles in muscle controlBiological Cybernetics, 1972