The influence of training data selection on performance of neural networks for control of non-linear systems
β Scribed by A.B. Bendtsen; Niels Jensen
- Publisher
- Elsevier Science
- Year
- 1992
- Weight
- 511 KB
- Volume
- 17
- Category
- Article
- ISSN
- 0066-4138
No coin nor oath required. For personal study only.
π SIMILAR VOLUMES
Bader, G. and E. Gehrke, On the performance of transputer networks for solving linear systems of equations,
multilayer recurrent neural network is proposed for on-line synthesis of minimum-norm linear feedback control systems through pole assignment. The proposed neural network approach uses a four-layer recurrent neural network for the on-line computation of feedback gain matrices with the minimum Froben
Some necessary and sufficient conditions are found for the existence of the optimal control for systems with a singular mean-square performance index. Optimal control is obtained by the use of pseudo-inverse. The asymptotic behavior of sub-optimal control is also studied.
In this paper, by means of the simulation techniques proposed the effects of several chassis controls (4WS, 2WS) on driver-vehicle closed loop system performance were simulated for young drivers and aged drivers based on a multi-loop driver model. The simulation results were analyzed based on the re