Iterative Learning from Positive Data and Negative Counterexamples

A model for learning in the limit is defined where a (so-called iterative) learner gets all positive examples from the target language, tests every new conjecture with a teacher (oracle) if it is a subset of the target language (and if it is not, then it receives a negative counterexample), and uses only limited long-term memory (incorporated in conjectures). Three variants of this model are compared: when a learner receives least negative counterexamples, the ones whose size is bounded by the maximum size of input seen so far, and arbitrary ones. A surprising result is that sometimes absence of bounded counterexamples can help an iterative learner whereas arbitrary counterexamples are useless. We also compare our learnability model with other relevant models of learnability in the limit, study how our model works for indexed classes of recursive languages, and show that learners in our model can work in non-U-shaped way-never abandoning the first right conjecture.

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

[2]  John Case,et al.  U-Shaped, Iterative, and Iterative-with-Counter Learning , 2007, COLT.

[3]  Chen Lin,et al.  Neural Information Processing -letters and Reviews Simplify Support Vector Machines by Iterative Learning , 2022 .

[4]  John Case,et al.  Memory-Limited U-Shaped Learning , 2006, COLT.

[5]  M. Bowerman Starting to talk worse: Clues to language acquisition from children's late speech errors , 1982 .

[6]  Sandra Zilles,et al.  Relations between Gold-style learning and query learning , 2005, Inf. Comput..

[7]  Akihiro Yamamoto,et al.  Learning Elementary Formal Systems , 1992, Theor. Comput. Sci..

[8]  Akihiro Yamamoto,et al.  Algorithmic Learning Theory with Elementary Formal Systems , 1992 .

[9]  Sandra Zilles,et al.  Comparison of Query Learning and Gold-Style Learning in Dependence of the Hypothesis Space , 2004, ALT.

[10]  Paul Young,et al.  An introduction to the general theory of algorithms , 1978 .

[11]  John Case,et al.  When unlearning helps , 2008, Inf. Comput..

[12]  Satoru Miyano,et al.  More About Learning Elementary Formal Systems , 1991, Nonmonotonic and Inductive Logic.

[13]  M. W. Shields An Introduction to Automata Theory , 1988 .

[14]  Rolf Wiehagen,et al.  Learning recursive languages from good examples , 2004, Annals of Mathematics and Artificial Intelligence.

[15]  Satoru Miyano,et al.  A machine discovery from amino acid sequences by decision trees over regular patterns , 1993, New Generation Computing.

[16]  Daniel N. Osherson,et al.  Systems That Learn: An Introduction to Learning Theory for Cognitive and Computer Scientists , 1990 .

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

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

[19]  Tao Jiang,et al.  Learning regular languages from counterexamples , 1988, COLT '88.

[20]  Gary James Jason,et al.  The Logic of Scientific Discovery , 1988 .

[21]  Manuel Blum,et al.  Toward a Mathematical Theory of Inductive Inference , 1975, Inf. Control..

[22]  Mark G. Pleszkoch,et al.  Learning Via Queries in $\lbrack +, < \rbrack$ , 1992 .

[23]  Dana Angluin,et al.  Queries and concept learning , 1988, Machine Learning.

[24]  Mark A. Fulk Prudence and Other Conditions on Formal Language Learning , 1990, Inf. Comput..

[25]  S. Pinker Formal models of language learning , 1979, Cognition.

[26]  Jochen Nessel,et al.  Learning erasing pattern languages with queries , 2005, Theor. Comput. Sci..

[27]  Carl H. Smith,et al.  On the impact of forgetting on learning machines , 1995, JACM.

[28]  Manuel Blum,et al.  A Machine-Independent Theory of the Complexity of Recursive Functions , 1967, JACM.

[29]  Achim Blumensath,et al.  Automatic structures , 2000, Proceedings Fifteenth Annual IEEE Symposium on Logic in Computer Science (Cat. No.99CB36332).

[30]  Sanjay Jain,et al.  Learning languages from positive data and a limited number of short counterexamples , 2007, Theor. Comput. Sci..

[31]  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 .

[32]  John Case,et al.  Machine Inductive Inference and Language Identification , 1982, ICALP.

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

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

[35]  Klaus P. Jantke,et al.  Combining Postulates of Naturalness in Inductive Inference , 1981, J. Inf. Process. Cybern..

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

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

[38]  Henning Fernau,et al.  Even linear simple matrix languages: formal language properties and grammatical inference , 2002, Theor. Comput. Sci..

[39]  Jr. Hartley Rogers Theory of Recursive Functions and Effective Computability , 1969 .

[40]  元木 達也 INDUCTIVE INFERENCE FROM ALL POSITIVE AND SOME NEGATIVE DATA , 1991 .

[41]  R. Treiman,et al.  Brown & Hanlon revisited: mothers' sensitivity to ungrammatical forms , 1984, Journal of Child Language.

[42]  Rolf Wiehagen A Thesis in Inductive Inference , 1990, Nonmonotonic and Inductive Logic.

[43]  Sanjay Jain,et al.  Learning Languages from Positive Data and Negative Counterexamples , 2004, ALT.

[44]  William I. Gasarch,et al.  Learning via queries , 1992, COLT '88.

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

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

[47]  Susumu Hayashi,et al.  Limit-Computable Mathematics and Its Applications , 2002, CSL.

[48]  Susumu Hayashi,et al.  Towards Limit Computable Mathematics , 2000, TYPES.

[49]  John Case,et al.  Language Learning with Some Negative Information , 1993, Journal of computer and system sciences (Print).

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

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

[52]  Takeshi Shinohara,et al.  Rich Classes Inferable from Positive Data: Length-Bounded Elementary Formal Systems , 1994, Inf. Comput..

[53]  John Case,et al.  Comparison of Identification Criteria for Machine Inductive Inference , 1983, Theor. Comput. Sci..

[54]  Rolf Wiehagen Limes-Erkennung rekursiver Funktionen durch spezielle Strategien , 1975, J. Inf. Process. Cybern..

[55]  Thomas Zeugmann,et al.  Incremental Learning from Positive Data , 1996, J. Comput. Syst. Sci..