Title :
Constructing deterministic finite-state automata in sparse recurrent neural networks
Author :
Omlin, Christian W. ; Giles, C. Lee
Author_Institution :
NEC Res. Inst., Princeton, NJ, USA
fDate :
27 Jun-2 Jul 1994
Abstract :
Presents an algorithm for encoding deterministic finite-state automata in sparse recurrent neural networks with sigmoidal discriminant functions and second-order weights. The authors prove that for particular weight strength values the regular languages accepted by DFAs and the constructed networks are identical
Keywords :
deterministic automata; finite automata; formal languages; recurrent neural nets; deterministic finite-state automata; encoding; regular languages; second-order weights; sigmoidal discriminant functions; sparse recurrent neural networks; Doped fiber amplifiers; Encoding; Equations; Intelligent networks; Learning automata; National electric code; Neural networks; Neurons; Recurrent neural networks;
Conference_Titel :
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1901-X
DOI :
10.1109/ICNN.1994.374417
