Inductive inference from positive data is powerful
COLT '90 Proceedings of the third annual workshop on Computational learning theory
Identification of unions of languages drawn from an identifiable class
COLT '89 Proceedings of the second annual workshop on Computational learning theory
Inductive inference of monotonic formal systems from positive data
New Generation Computing - Selected papers from the international workshop on algorithmic learning theory,1990
The correct definition of finite elasticity: corrigendum to identification of unions
COLT '91 Proceedings of the fourth annual workshop on Computational learning theory
Learning elementary formal systems
Theoretical Computer Science
Rich classes inferable from positive data
Information and Computation
Towards a mathematical theory of machine discovery from facts
Theoretical Computer Science - Special issue on algorithmic learning theory
Polynomial Time Inference of Extended Regular Pattern Languages
Proceedings of RIMS Symposium on Software Science and Engineering
STACS '94 Proceedings of the 11th Annual Symposium on Theoretical Aspects of Computer Science
Compactness and Learning of Classes of Unions of Erasing Regular Pattern Languages
ALT '02 Proceedings of the 13th International Conference on Algorithmic Learning Theory
A Negative Result on Inductive Inference of Extended Pattern Languages
ALT '02 Proceedings of the 13th International Conference on Algorithmic Learning Theory
Finding patterns common to a set of strings (Extended Abstract)
STOC '79 Proceedings of the eleventh annual ACM symposium on Theory of computing
Hi-index | 0.00 |
The present paper considers the learning problem of erasing primitive formal systems, PFSs for short, in view of inductive inference in Gold framework from positive examples. A PFS is a kind of logic program over strings called regular patterns, and consists of exactly two axioms of the forms p(π) ← and p(τ) ← p(x1),..., p(xn), where p is a unary predicate symbol, π and τ are regular patterns, and xis are distinct variables. A PFS is erasing or nonerasing according to allowing the empty string substitution for some variables or not. We investigate the learnability of the class PFSL of languages generated by the erasing PFSs satisfying a certain condition. We first show that the class PFSL has M-finite thickness. Moriyama and Sato showed that a language class with M-finite thickness is learnable if and only if there is a finite tell tale set for each language in the class. We then introduce a particular type of finite set of strings for each erasing PFS, and show that the set is a finite tell tale set of the language. These imply that the class PFSL is learnable from positive examples.