参考文献

1

Angluin,D. On the complexity of minimum inference of regular sets. Information and Control,39,337-350,1978.

2

Barto,A.G. Connectionist learning for control. In W.Miller, R. Sutton, and P.Werbos(Eds.), Neural networks for control. Cambridge,MA:MIT Press,1990.

3

Cleeremans,A. ,Servan-Schreiber,D. ,and McClelland,J. Finite state automata and simple recurrent networks. Neural Comp. 1(3),372,1989.

4

銅谷賢治： リカレントネットワークの学習アルゴリズム，計測と制御, 30,296-301,1991.

5

Fu,K.S. and Booth,T.L. Grammatical inference:Introduction and survey - Part I. IEEE Transactions on systems, Man and Cybernetics, 5,195-111,1975.

6

Giles,C.L., Miller,C.B., Chen,D.,Chen,H.H., Sun,G.Z., Lee,Y.C. Learning and extracting finite state automata with second-order recurrent neural networks. Neural Comp.4,393-405, 1992.

7

Giles,C.L., Horne,B.G., Lin,T. Learning a class of large finite state machines with a recurrent neural network. Neural Networks. 8(9),1359-1365,1995.

8

Hopcroft,J.E. and Ullman,J.D. Introduction to automata theory, languages, and computation. Reading, MA: Addison-Wesley,1979.

9

Kohavi,Z. Switching and finite automata theory (2nd edn.). New York: Mcgraw-Hill,1978.

10

Lang,K. Random DFAs can be approximately learned from sparse uniform examples. In Proceedings of the Fifth ACM Workshop on Coputational Learning Theory. ,1992.

11

Miller,C.B., Giles,C.L. Experimental Comparison of the Effect of Order in Recurrent Neural Networks. International Journal of Pattern Recognition and Artificial Intelligence, (Special Issue on Neural Networks), 7(4),849,1993.

12

Mozer,M.C. and Bachrach,J. Discovering the structure of a reactive environment by exploration. Neural Comp. 2(4),447-454, 1990.

13

Narendra,K.S. and Parthasarathy,K. Identification and control of dynamical systems using neural networks. IEEE Transactions on Neural Networks, 1,4-27, 1990.

14

Pollack,J.B. The Identification of dynamical recognizers. Machine Learning, 7(2/3),227-252, 1991.

15

坂和正敏，田中雅博： ニューロコンピューティング入門，森北出版，1997.

16

Sato,M. A real time learning algorithm for recurrent analog neural networks, Biol. Cybern.,62,2229-2232,1990.

17

Tomita,M. Dynamic construction of finite-state automata from examples using hill-climbing. Proc. Fourth Annu. Cogn. Sci. Conf., 105, 1982.

18

渡辺辰巳，郷原一寿，内川嘉樹： リカレントニューラルネットワークの各学習則に関する検討および学習曲面の形状， 電子情報通信学会論文誌，Vol.J 74-d-,No12,1776-1787,1991.

19

Watrous,R.L., and Kuhn,G.M., Induction of finite-state languages using second-order recurrent networks. Neural Comp. 4(3),406-414, 1992.

20

Williams,R.J.,and Zipser,D. A learning algorithm for continually running fully recurrent neural networks. Neural Comp. 1(2),270, 1989.

21

Williams,R.J.,and Zipser,D. Gradient-based learning algorithms for recurrent networks and their computational complexity. in Y. Chauvin and D.E. Rumelhart(eds.) Backpropagation: Theory, Architectures, and Applications, Lawrence Erlbaum Associate, Publishers, New Jersey,434-486, 1995.