Systems that learn: an introduction to learning theory for cognitive and computer scientists
Systems that learn: an introduction to learning theory for cognitive and computer scientists
Theory of recursive functions and effective computability
Theory of recursive functions and effective computability
Prudence and other conditions on formal language learning
Information and Computation
On the power of inductive inference from good examples
Theoretical Computer Science
Regular Article: Open problems in “systems that learn”
Proceedings of the 30th IEEE symposium on Foundations of computer science
Machine Inductive Inference and Language Identification
Proceedings of the 9th Colloquium on Automata, Languages and Programming
Prescribed Learning of R.E. Classes
ALT '07 Proceedings of the 18th international conference on Algorithmic Learning Theory
Non U-shaped vacillatory and team learning
ALT'05 Proceedings of the 16th international conference on Algorithmic Learning Theory
Memory-limited u-shaped learning
COLT'06 Proceedings of the 19th annual conference on Learning Theory
Some recent results in u-shaped learning
TAMC'06 Proceedings of the Third international conference on Theory and Applications of Models of Computation
Variations on u-shaped learning
COLT'05 Proceedings of the 18th annual conference on Learning Theory
| Hi-index | 0.00 |
Overregularization seen in child language learning, re verb tense constructs, involves abandoning correct behaviors for incorrect ones and later reverting to correct behaviors. Quite a number of other child development phenomena also follow this U-shaped form of learning, unlearning, and relearning. A decisive learner doesn't do this and, in general, never abandons an hypothesis H for an inequivalent one where it later conjectures an hypothesis equivalent to H. The present paper shows that decisiveness is a real restriction on Gold's model of iteratively (or in the limit) learning of grammars for languages from positive data. This suggests that natural U-shaped learning curves may not be a mere accident in the evolution of human learning, but may be necessary for learning. The result also solves an open problem. Second-time decisive learners conjecture each of their hypotheses for a language at most twice. By contrast, they are shown not to restrict Gold's model of learning, and correspondingly, there is an apparent lack of reports in child development of the opposite, W-shaped learning curves.