Variations on U-shaped learning

The paper deals with the following problem: is returning to wrong conjectures necessary to achieve full power of algorithmic learning? Returning to wrong conjectures complements the paradigm of U-shaped learning when a learner returns to old correct conjectures. We explore our problem for classical models of learning in the limit from positive data: explanatory learning (when a learner stabilizes in the limit on a correct grammar) and behaviourally correct learning (when a learner stabilizes in the limit on a sequence of correct grammars representing the target concept). In both cases we show that returning to wrong conjectures is necessary to achieve full learning power. In contrast, one can modify learners (without losing learning power) such that they never show inverted U-shaped learning behaviour, that is, never return to old wrong conjecture with a correct conjecture in-between. Furthermore, one can also modify a learner (without losing learning power) such that it does not return to old "overinclusive" conjectures containing non-elements of the target language. We also consider our problem in the context of vacillatory learning (when a learner stabilizes on a finite number of correct grammars) and show that each of the following four constraints is restrictive (that is, reduces learning power): the learner does not return to old wrong conjectures; the learner is not inverted U-shaped; the learner does not return to old overinclusive conjectures; the learner does not return to old overgeneralizing conjectures. We also show that learners that are consistent with the input seen so far can be made decisive: on any text, they do not return to any old conjectures--wrong or right.

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

[2]  Patrick Brézillon,et al.  Lecture Notes in Artificial Intelligence , 1999 .

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

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

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

[6]  John R. Anderson,et al.  Why do children learn to say “Broke”? A model of learning the past tense without feedback , 2002, Cognition.

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

[8]  Susan Carey,et al.  7 – Face Perception: Anomalies of Development1 , 1982 .

[9]  John Case,et al.  U-shaped learning may be necessary 3 , 2004 .

[10]  K. Popper,et al.  The Logic of Scientific Discovery , 1960 .

[11]  S Pinker,et al.  Overregularization in language acquisition. , 1992, Monographs of the Society for Research in Child Development.

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

[13]  Rolf Wiehagen,et al.  Charakteristische Eigenschaften von erkennbaren Klassen rekursiver Funktionen , 1976, J. Inf. Process. Cybern..

[14]  John Case,et al.  The Power of Vacillation in Language Learning , 1999, SIAM J. Comput..

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

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

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

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

[19]  V. Marchman,et al.  U-shaped learning and frequency effects in a multi-layered perception: Implications for child language acquisition , 1991, Cognition.

[20]  Robin Milner,et al.  On Observing Nondeterminism and Concurrency , 1980, ICALP.

[21]  Sanjay Jain,et al.  Open Problems in "Systems That Learn" , 1994, J. Comput. Syst. Sci..

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

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

[24]  Stuart A. Kurtz,et al.  Prudence in language learning , 1988, COLT '88.

[25]  Michael Stob,et al.  An analysis of a learning paradigm , 1986 .

[26]  Sanjay Jain,et al.  Variations on U-Shaped Learning , 2005, COLT.

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

[28]  Leslie B. Cohen,et al.  Beyond U-Shaped Development in Infants' Processing of Faces: An Information-Processing Account , 2004 .

[29]  R. Stavy,et al.  U-shaped behavioral growth , 1982 .