Fool's Gold: Extracting Finite State Machines from Recurrent Network Dynamics

Several recurrent networks have been proposed as representations for the task of formal language learning. After training a recurrent network recognize a formal language or predict the next symbol of a sequence, the next logical step is to understand the information processing carried out by the network. Some researchers have begun to extracting finite state machines from the internal state trajectories of their recurrent networks. This paper describes how sensitivity to initial conditions and discrete measurements can trick these extraction methods to return illusory finite state descriptions.

[1]  Noam Chomsky,et al.  वाक्यविन्यास का सैद्धान्तिक पक्ष = Aspects of the theory of syntax , 1965 .

[2]  E. Mark Gold,et al.  Language Identification in the Limit , 1967, Inf. Control..

[3]  Allen Newell,et al.  Computer science as empirical inquiry: symbols and search , 1976, CACM.

[4]  Jeffrey D. Ullman,et al.  Introduction to Automata Theory, Languages and Computation , 1979 .

[5]  David Zipser,et al.  Feature Discovery by Competive Learning , 1986, Cogn. Sci..

[6]  Dana Angluin,et al.  Learning Regular Sets from Queries and Counterexamples , 1987, Inf. Comput..

[7]  Michael F. Barnsley,et al.  Fractals everywhere , 1988 .

[8]  James L. McClelland,et al.  Finite State Automata and Simple Recurrent Networks , 1989, Neural Computation.

[9]  Robert L. Devaney Pallarés.  An introduction to chaotic dynamical systems , 1989 .

[10]  Jeffrey L. Elman,et al.  Finding Structure in Time , 1990, Cogn. Sci..

[11]  Michael I. Jordan,et al.  Advances in Neural Information Processing Systems 30 , 1995 .

[12]  Raymond L. Watrous,et al.  Induction of Finite-State Automata Using Second-Order Recurrent Networks , 1991, NIPS.

[13]  C. Lee Giles,et al.  Extracting and Learning an Unknown Grammar with Recurrent Neural Networks , 1991, NIPS.

[14]  James P. Crutchfield,et al.  Computation at the Onset of Chaos , 1991 .

[15]  M. Bernhard.  Introduction to Chaotic Dynamical Systems , 1992 .

[16]  Padhraic Smyth,et al.  Learning Finite State Machines With Self-Clustering Recurrent Networks , 1993, Neural Computation.

[17]  J. Kolen.  Recurrent Networks: State Machines Or Iterated Function Systems? , 1994 .

[18]  John F. Kolen,et al.  The observers' paradox: apparent computational complexity in physical systems , 1995, J. Exp. Theor. Artif. Intell..