论文信息 - Inductive Inference of Tree Automata by Recursive Neural Networks

Inductive Inference of Tree Automata by Recursive Neural Networks

Recurrent neural networks are powerful learning machines capable of processing sequences. A recent extension of these machines can conveniently be used to process also general data structures like trees and graphs, which opens the doors to a number of new very interesting applications previously unexplored.

[1] Carl H. Smith,et al. Inductive Inference: Theory and Methods , 1983, CSUR.

[2] Alessandro Sperduti,et al. Supervised neural networks for the classification of structures , 1997, IEEE Trans. Neural Networks.

[3] Raymond L. Watrous,et al. Induction of Finite-State Languages Using Second-Order Recurrent Networks , 1992, Neural Computation.

[4] Michael A. Arbib,et al. Algebra Automata I: Parallel Programming as a Prolegomena to the Categorical Approach , 1968, Inf. Control..

[5] C. Lee Giles,et al. Constructing deterministic finite-state automata in recurrent neural networks , 1996, JACM.

[6] Colin Giles,et al. Learning, invariance, and generalization in high-order neural networks. , 1987, Applied optics.

[7] Taylor L. Booth,et al. Grammatical Inference: Introduction and Survey - Part I , 1975, IEEE Trans. Syst. Man Cybern..

[8] Sontag,et al. Backpropagation separates when perceptrons do , 1989 .

[9] C. Lee Giles,et al. Learning and Extracting Finite State Automata with Second-Order Recurrent Neural Networks , 1992, Neural Computation.

[10] C. Lee Giles,et al. Experimental Comparison of the Effect of Order in Recurrent Neural Networks , 1993, Int. J. Pattern Recognit. Artif. Intell..

[11] james w.thatcher,et al. tree automata: an informal survey , 1974 .