Learnability of automatic classes

Learnability of Automatic Classes

The present work initiates the study of the learnability of automatic indexable classes which are classes of regular languages of a certain form. Angluin’s tell-tale condition characterises when these classes are explanatorily learnable. Therefore, the more interesting question is when learnability holds for learners with complexity bounds, formulated in the automata-theoretic setting. The lear...

On the Learnability of Rich Function Classes

The probably approximately correct (PAC) model of learning and its extension to real-valued function classes sets a rigorous framework based upon which the complexity of learning a target from a function class using a finite sample can be computed. There is one main restriction, however, that the function class have a finite VC-dimension or scale-sensitive pseudo-dimension. In this paper we pre...

Learnability of Some Classes of Optimal Categorial Grammars

In this paper we characterize a learnable class of classical categorial grammars, which lies inbetween (learnable) class of rigid grammars and (not learnable) class of optimal grammars. The learning function we provide is based on guided optimal unification, introduced in our paper Marciniec (2004).

Learnability and Characterization Results for Classes of Boolean Functions

Automatic Detection of Learnability under Unreliable and Sparse User Feedback

Personalization for real-world machine-learning applications usually has to incorporate user feedback. Unfortunately, user feedback often suffers from sparsity and possible inconsistencies. Here we present an algorithm that exploits feedback for learning only when it is consistent. The user provides feedback on a small subset of the data. Based on the data representation alone, our algorithm em...