Abstract
In this investigation, a new algorithm is developed for the updating of a neural network. It is concentrated in a fuzzy transition between the recursive least square and extended Kalman filter algorithms with the purpose to get a bounded gain such that a satisfactory modeling could be maintained. The advised algorithm has the advantage compared with the mentioned methods that it eludes the excessive increasing or decreasing of its gain. The gain of the recommended algorithm is uniformly stable and its convergence is found. The new algorithm is employed for
the modeling of two synthetic examples.
| Original language | English |
|---|---|
| Pages (from-to) | 79-95 |
| Number of pages | 17 |
| Journal | Kybernetika |
| Volume | 54 |
| Issue number | 1 |
| DOIs | |
| Publication status | Published - 2018 |
Fields of science
- 101 Mathematics
- 101013 Mathematical logic
- 101024 Probability theory
- 102001 Artificial intelligence
- 102003 Image processing
- 102019 Machine learning
- 603109 Logic
- 202027 Mechatronics
JKU Focus areas
- Computation in Informatics and Mathematics
- Mechatronics and Information Processing
- Nano-, Bio- and Polymer-Systems: From Structure to Function