On the amount of nonconstructivity in learning formal languages from text

Abstract Nonconstructive computations by various types of machines and automata have been considered by, for example, Karp and Lipton [21] , and Freivalds [9] , [10] . They allow to regard more complicated algorithms from the viewpoint of much more primitive computational devices. The amount of nonconstructivity is a quantitative characterization of the distance between types of computational devices with respect to solving a specific problem. This paper studies the amount of nonconstructivity needed to learn classes of formal languages. Different learning types are compared with respect to the amount of nonconstructivity needed to learn indexable classes and recursively enumerable classes, respectively, of formal languages from positive data. Matching upper and lower bounds for the amount of nonconstructivity needed are shown.

[1]  Sanjay Jain,et al.  On the Amount of Nonconstructivity in Learning Formal Languages from Positive Data , 2012, TAMC.

[2]  John Case,et al.  Periodicity in generations of automata , 1974, Mathematical systems theory.

[3]  Arun Sharma,et al.  On Monotonic Strategies for Learning r.e. Languages , 1994, AII/ALT.

[4]  Jan Krajícek,et al.  Consequences of the provability of NP ⊆ P/poly , 2007, J. Symb. Log..

[5]  Arun Sharma,et al.  Generalization and specialization strategies for learning r.e. languages , 2004, Annals of Mathematics and Artificial Intelligence.

[6]  Rusins Freivalds,et al.  Amount of Nonconstructivity in Finite Automata , 2009, CIAA.

[7]  Frank Stephan,et al.  Language Learning from Texts: Mindchanges, Limited Memory, and Monotonicity , 1995, Inf. Comput..

[8]  Rusins Freivalds,et al.  On the Amount of Nonconstructivity in Learning Recursive Functions , 2011, TAMC.

[9]  P. Erdös.  Some remarks on the theory of graphs , 1947 .

[10]  Arun Sharma,et al.  Computational Limits on Team Identification of Languages , 1996, Inf. Comput..

[11]  Carl H. Smith,et al.  The Power of Pluralism for Automatic Program Synthesis , 1982, JACM.

[12]  Thomas Zeugmann,et al.  Learning indexed families of recursive languages from positive data: A survey , 2008, Theor. Comput. Sci..

[13]  Dana Angluin,et al.  Finding Patterns Common to a Set of Strings , 1980, J. Comput. Syst. Sci..

[14]  Klaus P. Jantke.  Monotonic and non-monotonic inductive inference , 2009, New Generation Computing.

[15]  Markus Holzer,et al.  Automata That Take Advice , 1995, MFCS.

[16]  Rolf Wiehagen,et al.  Learning languages and functions by erasing , 2000, Theor. Comput. Sci..

[17]  Rusins Freivalds,et al.  Co-Learning of Recursive Languages from Positive Data , 1996, Ershov Memorial Conference.

[18]  Thomas Zeugmann,et al.  Language learning in dependence on the space of hypotheses , 1993, COLT '93.

[19]  Dana Angluin,et al.  Inductive Inference of Formal Languages from Positive Data , 1980, Inf. Control..

[20]  Olaf Beyersdorff,et al.  Proof systems that take advice , 2011, Inf. Comput..

[21]  Thomas Zeugmann,et al.  A Guided Tour Across the Boundaries of Learning Recursive Languages , 1995, GOSLER Final Report.

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

[23]  Derick Wood,et al.  Theory of computation , 1986 .

[24]  Rusins Freivalds,et al.  Amount of nonconstructivity in deterministic finite automata , 2010, Theor. Comput. Sci..

[25]  Thomas Zeugmann,et al.  Types of monotonic language learning and their characterization , 1992, COLT '92.