Comparison of Backpropagation and Kalman Filter-based Training for Neural Networks
Research output: Contributions to collected editions/works › Article in conference proceedings › Research › peer-review
Authors
This work describes and compares the backpropagation algorithm with the extended Kalman filter (EKF), a second-order training method which can be applied to the problem of learning neural network parameters and is known to converge in only a few iterations. The algorithms are compared with respect to their effectiveness and speed of convergence using simulated data for both, a regression and a classification task.
| Original language | English |
|---|---|
| Title of host publication | 2021 25th International Conference on System Theory, Control and Computing (ICSTCC) : October 20 – 23, 2021 Iași, ROMANIA, Proceedings |
| Editors | Lavinia Ferariu, Mihaela-Hanako Matcovschi, Florina Ungureanu |
| Number of pages | 8 |
| Place of Publication | Piscataway |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Publication date | 20.10.2021 |
| Pages | 234-241 |
| ISBN (print) | 978-1-6654-3055-5 |
| ISBN (electronic) | 978-1-6654-1496-8 |
| DOIs | |
| Publication status | Published - 20.10.2021 |
| Event | 25th International Conference on System Theory, Control and Computing - Iasi, Romania Duration: 20.10.2021 → 23.10.2021 Conference number: 25 https://ieeexplore.ieee.org/xpl/conhome/9607028/proceeding |
- Backpropagation Algorithm, Kalman Filter, Neural Networks
- Engineering