Learning techniques and neural networks for the solution of \(N\)-stage nonlinear nonquadratic optimal control problems (Q4026322)
From MaRDI portal
!
This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:
scientific article; zbMATH DE number 124702
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | Learning techniques and neural networks for the solution of \(N\)-stage nonlinear nonquadratic optimal control problems |
scientific article; zbMATH DE number 124702 |
Statements
21 February 1993
0 references
optimal control
0 references
nonlinear discrete-time dynamic systems
0 references
backpropagation
0 references
multi-layer feed forward neural networks
0 references
learning
0 references
0.9259131
0 references
0.9100213
0 references
0 references
0 references
0.90660346
0 references
0.90454096
0 references
Learning techniques and neural networks for the solution of \(N\)-stage nonlinear nonquadratic optimal control problems (English)
0 references
[For the entire collection see Zbl 0745.00051.] Nonlinear discrete-time dynamic systems are considered in this paper. A closed loop feed forward control strategy is to be determined such that a cost function is minimized. The problem is solved by constraining the control strategies to take on the form of a suitable configuration of multi-layer feed forward neural networks connected to one another. Backpropagation is applied to derive optimal values of the synaptic weights. Three examples are given to show the learning properties of the neural control strategy.
0 references
