Robust learning of automatic classes of languages

One of the most important paradigms in the inductive inference literature is that of robust learning. This paper adapts and investigates the paradigm of robust learning to learning languages from positive data. Broadening the scope of that paradigm is important: robustness captures a form of invariance of learnability under admissible transformations on the object of study; hence, it is a very desirable property. The key to defining robust learning of languages is to impose that the latter be automatic, that is, recognisable by a finite automaton. The invariance property used to capture robustness can then naturally be defined in terms of first-order definable operators, called translators. For several learning criteria amongst a selection of learning criteria investigated either in the literature on explanatory learning from positive data or in the literature on query learning, we characterise the classes of languages all of whose translations are learnable under that criterion. Paradigm of robust learning in the limit is generalised from functions to languages.Characterisations are provided for robust learning under various criteria.Connections between Robust query learning and learning in the limit are shown.

[1]  Thomas Zeugmann On Barzdin's Conjecture , 1986, AII.

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

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

[4]  Rolf Wiehagen,et al.  Learning and Consistency , 1995, GOSLER Final Report.

[5]  Mark A. Fulk Robust separations in inductive inference , 1990, Proceedings [1990] 31st Annual Symposium on Foundations of Computer Science.

[6]  Daniel N. Osherson,et al.  Criteria of Language Learning , 1982, Inf. Control..

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

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

[9]  Robert H. Sloan,et al.  BOOK REVIEW: "SYSTEMS THAT LEARN: AN INTRODUCTION TO LEARNING THEORY, SECOND EDITION", SANJAY JAIN, DANIEL OSHERSON, JAMES S. ROYER and ARUN SHARMA , 2001 .

[10]  Frank Stephan,et al.  Avoiding coding tricks by hyperrobust learning , 2002, Theor. Comput. Sci..

[11]  Sanjay Jain,et al.  ON AUTOMATIC FAMILIES , 2011 .

[12]  Sandra Zilles,et al.  Formal language identification: query learning vs. Gold-style learning , 2004, Inf. Process. Lett..

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

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

[15]  M. Rabin Automata on Infinite Objects and Church's Problem , 1972 .

[16]  Sanjay Jain,et al.  A Tour of Robust Learning , 2003 .

[17]  Sasha Rubin,et al.  Automatic Structures: Overview and Future Directions , 2003, J. Autom. Lang. Comb..

[18]  Sanjay Jain,et al.  Learnability of automatic classes , 2012, J. Comput. Syst. Sci..

[19]  Anil Nerode,et al.  Automatic Presentations of Structures , 1994, LCC.

[20]  Carl H. Smith,et al.  Robust Learning Is Rich , 2001, J. Comput. Syst. Sci..