Learning and Classifying
We define and study a learning paradigm that sits between identification in the limit and classification. More precisely, we expect that a learner be able to identify in the limit which members of a set D of n possible data belong to a target language, where n and D are arbitrary. We show that Ex- and BC-learning are often more difficult than performing this classification task, taking into account desirable constraints on how the learner behaves, such as bounding the number of mind changes and being conservative. Special attention is given to various forms of consistency. We provide a fairly comprehensive set of results that demonstrate the fruitfulness of the approach and the richness of the paradigm.
KeywordsInitial Segment Unique Member Recursive Function Inductive Inference Boolean Combination
Unable to display preview. Download preview PDF.
- [Bār74a]Bārzdiņš, J.: Inductive inference of automata, functions and programs. In: Proceedings of the 20th International Congress of Mathematicians, Vancouver, pp. 455–560 (1974) (in Russian); English translation in American Mathematical Society Translations: Series 2, 109, 107–112 (1977)Google Scholar
- [Bār74b]Bārzdiņš, J.: Two theorems on the limiting synthesis of functions. In: Theory of Algorithms and Programs, vol. 1, pp. 82–88. Latvian State University (1974) (in Russian)Google Scholar
- [JORS99]Jain, S., Osherson, D., Royer, J., Sharma, A.: Systems that Learn: An Introduction to Learning Theory, 2nd edn. MIT Press, Cambridge (1999)Google Scholar