Abstract | ||
---|---|---|
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. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1109/TNN.2010.2059040 | IEEE Transactions on Neural Networks |
Keywords | Field | DocType |
automata,finite state automaton,system identification,identification,encoding,cost function,dynamic system,finite state machines,discrete time,recurrent neural networks,simulated annealing,finite state automata,recurrent neural network | Simulated annealing,Computer science,Automaton,Recurrent neural network,Algorithm,Finite-state machine,Artificial intelligence,System identification,Artificial neural network,Machine learning,Encoding (memory),Levenberg–Marquardt algorithm | Journal |
Volume | Issue | ISSN |
21 | 9 | 1045-9227 |
Citations | PageRank | References |
6 | 0.46 | 20 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Sung Hwan Won | 1 | 7 | 1.18 |
Iickho Song | 2 | 558 | 85.31 |
Sun-Young Lee | 3 | 96 | 12.49 |
cheol hoon | 4 | 178 | 30.78 |