How to construct random functions
Journal of the ACM (JACM)
On the learnability of Boolean formulae
STOC '87 Proceedings of the nineteenth annual ACM symposium on Theory of computing
The complexity of Boolean functions
The complexity of Boolean functions
Learning regular sets from queries and counterexamples
Information and Computation
Functions comuted by monotone boolean formulas with no repeated variables
Theoretical Computer Science
Negative Results for Equivalence Queries
Machine Learning
Learning in the presence of finitely or infinitely many irrelevant attributes
COLT '91 Proceedings of the fourth annual workshop on Computational learning theory
Learning read-once formulas with queries
Journal of the ACM (JACM)
Structure identification in relational data
Artificial Intelligence - Special volume on constraint-based reasoning
Lower Bound Methods and Separation Results for On-Line Learning Models
Machine Learning - Computational learning theory
Learning Conjunctions of Horn Clauses
Machine Learning - Computational learning theory
Combinatorial characterization of read-once formulae
Discrete Mathematics - Special issue on combinatorics and algorithms
Model theory and computer science: an appetizer
Handbook of logic in computer science (vol. 1)
Probabilistic revision of logical domain theories
Probabilistic revision of logical domain theories
Asking questions to minimize errors
COLT '93 Proceedings of the sixth annual conference on Computational learning theory
Cryptographic limitations on learning Boolean formulae and finite automata
Journal of the ACM (JACM)
Theory refinement combining analytical and empirical methods
Artificial Intelligence
Knowledge-based artificial neural networks
Artificial Intelligence
When won't membership queries help?
Selected papers of the 23rd annual ACM symposium on Theory of computing
Read-twice DNF formulas are properly learnable
Euro-COLT '93 Proceedings of the first European conference on Computational learning theory
Fast learning of k-term DNF formulas with queries
Journal of Computer and System Sciences - Special issue on selected papers presented at the 24th annual ACM symposium on the theory of computing (STOC '92)
Exact learning Boolean functions via the monotone theory
Information and Computation
Matters horn and other features in the computational learning theory landscape: the notion of membership
Logical settings for concept-learning
Artificial Intelligence
Attribute-efficient learning in query and mistake-bound models
Journal of Computer and System Sciences
Complexity theoretic hardness results for query learning
Computational Complexity
The complexity of theory revision
Artificial Intelligence
On theory revision with queries
COLT '99 Proceedings of the twelfth annual conference on Computational learning theory
The Semantics of Predicate Logic as a Programming Language
Journal of the ACM (JACM)
More theory revision with queries (extended abstract)
STOC '00 Proceedings of the thirty-second annual ACM symposium on Theory of computing
Machine Learning
Effective and Efficient Knowledge Base Refinement
Machine Learning
Concept Formation and Knowledge Revision
Concept Formation and Knowledge Revision
Propositional Logic: Deduction and Algorithms
Propositional Logic: Deduction and Algorithms
Switching and Finite Automata Theory: Computer Science Series
Switching and Finite Automata Theory: Computer Science Series
Adaptive Versus Nonadaptive Attribute-Efficient Learning
Machine Learning
Theory Revision with Queries: DNF Formulas
Machine Learning
Machine Learning
Machine Learning
Improved Algorithms for Theory Revision with Queries
COLT '00 Proceedings of the Thirteenth Annual Conference on Computational Learning Theory
Tractability of theory patching
Journal of Artificial Intelligence Research
The Journal of Machine Learning Research
Theoretical Computer Science
Projective DNF formulae and their revision
Discrete Applied Mathematics
Proceedings of the 2010 conference on ECAI 2010: 19th European Conference on Artificial Intelligence
COLT'06 Proceedings of the 19th annual conference on Learning Theory
Hi-index | 0.00 |
A theory, in this context, is a Boolean formula; it is used to classify instances, or truth assignments. Theories can model real-world phenomena, and can do so more or less correctly. The theory revision, or concept revision, problem is to correct a given, roughly correct concept. This problem is considered here in the model of learning with equivalence and membership queries. A revision algorithm is considered efficient if the number of queries it makes is polynomial in the revision distance between the initial theory and the target theory, and polylogarithmic in the number of variables and the size of the initial theory. The revision distance is the minimal number of syntactic revision operations, such as the deletion or addition of literals, needed to obtain the target theory from the initial theory. Efficient revision algorithms are given for Horn formulas and read-once formulas, where revision operators are restricted to deletions of variables or clauses, and for parity formulas, where revision operators include both deletions and additions of variables. We also show that the query complexity of the read-once revision algorithm is near-optimal.