论文信息 - Neural network architecture for adaptive system modeling and control

Neural network architecture for adaptive system modeling and control

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. >

Levin | Gewirtzman | Inbar

[1] M. Kawato,et al. Hierarchical neural network model for voluntary movement with application to robotics , 1988, IEEE Control Systems Magazine.

[2] G F Inbar,et al. Parameter and signal adaptation in the stretch reflex loop. , 1976, Progress in brain research.

[3] Bernard Widrow,et al. Neural nets for adaptive filtering and adaptive pattern recognition , 1988, Computer.

[4] A. Sideris,et al. A multilayered neural network controller , 1988, IEEE Control Systems Magazine.

[5] Esther Levin,et al. A recurrent neural network: Limitations and training , 1990, Neural Networks.

[6] Neri Merhav,et al. The estimation of the model order in exponential families , 1989, IEEE Trans. Inf. Theory.

[7] R. K. Elsley,et al. A learning architecture for control based on back-propagation neural networks , 1988, IEEE 1988 International Conference on Neural Networks.

[8] Richard P. Lippmann,et al. An introduction to computing with neural nets , 1987 .

[9] H. Akaike. A new look at the statistical model identification , 1974 .