Mind Change Complexity of Learning Logic Programs [chapter]

Sanjay Jain, Arun Sharma
1999 Lecture Notes in Computer Science  
The present paper motivates the study of mind change complexity for learning minimal models of length-bounded logic programs. It establishes ordinal mind change complexity bounds for learnability of these classes both from positive facts and from positive and negative facts. Preprint submitted to Elsevier Science 1 The learnability analysis of ILP in the learning by query model is able to overcome some of the restrictive nature of the PAC model by allowing the learner queries to an oracle. For
more » ... xamples of such analysis, see Khardon [Kha98] and Krishna-Rao and Sattar [KRS98]. 2 Arikawa [Ari70] adapted Smullyan's [Smu61] elementary formal systems (EFS) for investigation of formal languages. Later, Arikawa et al. [ASY92] showed that EFS can be viewed as a logic programming language over strings. Recently, various subclasses of EFS have been investigated in the context of learnability (e.g., see
doi:10.1007/3-540-49097-3_16 fatcat:qc3kyoumirhnbcf5w4wjojiwvu