On-line Inference of Finite Automata in Noisy Environments
The most common type of noise in continuous systems of the real world is Gaussian noise, whereas discrete environments are usually subject to noise of a discrete type. The established, original solution for on-line inference of finite automata that is based on generalized recurrent neural networks is evaluated in the presence of noise of both types. It showed quite good performance and robustness.
KeywordsProblem Domain Recurrent Neural Network Noisy Environment Finite Automaton Continuous Type
Unable to display preview. Download preview PDF.
- Gabrijel, I. (2002) Generalized Architecture of Recurrent Neural Networks and On-Line Identification of Finite Automata — PhD. Thesis. University of Ljubljana, Faculty of Computer and Information Science, Ljubljana, Slovenia.Google Scholar
- Gabrijel, I., Dobnikar, A. (2001) On-line identification and rule extraction of finite state automata with recurrent neural networks. In: Kurkova, V., Steele, N. C., Neruda, R., Karny, M. (eds.) Proceedings of the International Conference on Artificial Neural Nets and Genetic Algorithms. Springer-Verlag, Vienna, Austria, pp. 78–81.Google Scholar
- Gabrijel, I., Dobnikar, A. (2003) Generalized recurrent neural networks and continuous dynamic systems. In: Pearson, D. W., Steele, N. C, Albrecht, R. (eds.) Proceedings of the International Conference on Artificial Neural Nets and Genetic Algorithms. Springer-Verlag, Vienna, Austria, pp. 9–12.Google Scholar