A Computation Modification for Multi-layered Neural Network Using Extended Kalman Filter
| Autor: | Kyungsup Kim, Hui-Joon Kim, Yu-Jae Won |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Computational complexity theory
Artificial neural network Estimation theory Computer science Computation 02 engineering and technology Kalman filter 01 natural sciences 010309 optics Reduction (complexity) Extended Kalman filter 0103 physical sciences 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Algorithm Free parameter |
| Zdroj: | Proceedings of the 10th International Conference on Computer Modeling and Simulation. |
| DOI: | 10.1145/3177457.3177463 |
| Popis: | A lot of learning algorithms for deep layered network are sincerely suffered from complex computation and slow convergence because of a very large number of free parameters. We need to develop an efficient algorithm for deep neural network. The Kalman filter concept can be applied to parameter estimation of neural network to improve computation performance. The algorithms based extended Kalman filter has a serious drawback in its computational complexity. We discuss how a fast algorithm should be developed for reduction in computation time. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|