Abstract
Artificial neural networks find wide applications in control engineering, image recognition, classification and optimization of different processes. However, for the solution of high order optimization tasks, efficiency of artificial neural networks may decrease because of high growth of expenses for the development of a composite artificial neural network and, especially, for its tuning for applied tasks. This paper presents the method of decomposition of high order optimization tasks into the series of lower order tasks. This allows one to significantly speed up the solution of the tasks with application of uniform artificial neural networks of parallel action. Decomposition procedure is formed using incidence matrices and vectors in conjunction with the threshold level of intensity of interconnections in the optimization system.
| Original language | English |
|---|---|
| Pages | 37 - 41 |
| DOIs | |
| Publication status | Published - 2002 |
| Event | International Conference on Control Applications - Glasgow, United Kingdom Duration: 18 Sept 2002 → 20 Sept 2002 |
Conference
| Conference | International Conference on Control Applications |
|---|---|
| Country/Territory | United Kingdom |
| City | Glasgow |
| Period | 18/09/02 → 20/09/02 |
Bibliographical note
The full text is not available on the repository.Keywords
- neural nets
- optimal control
- optimisation
- parallel processing
- decomposition
- homogeneous neural network
- optimization
- parallelism
- Artificial intelligence
- Artificial neural networks
- Biological neural networks
- Control systems
- Cost function
- Large-scale systems
- Matrix decomposition
- Neural networks
- Optimization methods
- Radio control