Identification of finite state automata with a class of recurrent neural networks
| Autor: | Sun Young Lee, Lickho Song, Sung Hwan Won, Cheol Hoon Park |
|---|---|
| Rok vydání: | 2010 |
| Předmět: |
Computer Networks and Communications
Computer science Inference Dynamical system Automation Artificial Intelligence Encoding (memory) Computer Simulation Problem Solving Finite-state machine Artificial neural network business.industry System identification Recurrent neural nets General Medicine Mathematical Concepts Models Theoretical Computer Science Applications Automaton Identification (information) Recurrent neural network Simulated annealing Artificial intelligence Neural Networks Computer business Algorithm Software Algorithms |
| Zdroj: | IEEE transactions on neural networks. 21(9) |
| ISSN: | 1941-0093 |
| Popis: | A class of recurrent neural networks is proposed and proven to be capable of identifying any discrete-time dynamical system. The application of the proposed network is addressed in the encoding, identification, and extraction of finite state automata (FSAs). Simulation results show that the identification of FSAs using the proposed network, trained by the hybrid greedy simulated annealing with a modified cost function in the training stage, generally exhibits better performance than the conventional identification procedures. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|