Foundations of a functional approach to knowledge representation.
Artificial Intelligence
Quantifying inductive bias: AI learning algorithms and Valiant's learning framework
Artificial Intelligence
A general lower bound on the number of examples needed for learning
Information and Computation
Connectionist learning procedures
Artificial Intelligence
Learnability and the Vapnik-Chervonenkis dimension
Journal of the ACM (JACM)
Results on learnability and the Vapnick-Chervonenkis dimension
COLT '88 Proceedings of the first annual workshop on Computational learning theory
Hierarchical knowledge bases and efficient disjunctive reasoning
Proceedings of the first international conference on Principles of knowledge representation and reasoning
Some results on the computational complexity of refining confidence factors
International Journal of Approximate Reasoning
Completeness in approximation classes
Information and Computation
PAC-learnability of determinate logic programs
COLT '92 Proceedings of the fifth annual workshop on Computational learning theory
Toward efficient agnostic learning
COLT '92 Proceedings of the fifth annual workshop on Computational learning theory
Structure identification in relational data
Artificial Intelligence - Special volume on constraint-based reasoning
Symbolic knowledge and neural networks: insertion, refinement and extraction
Symbolic knowledge and neural networks: insertion, refinement and extraction
On the complexity of propositional knowledge base revision, updates, and counterfactuals
Artificial Intelligence
C4.5: programs for machine learning
C4.5: programs for machine learning
On the hardness of approximating minimization problems
STOC '93 Proceedings of the twenty-fifth annual ACM symposium on Theory of computing
Theory refinement combining analytical and empirical methods
Artificial Intelligence
The refinement of probabilistic rule sets: sociopathic interactions
Artificial Intelligence
AAAI '94 Proceedings of the twelfth national conference on Artificial intelligence (vol. 1)
Incremental recompilation of knowledge (extended abstract)
AAAI'94 Proceedings of the twelfth national conference on Artificial intelligence (vol. 2)
AAAI'94 Proceedings of the twelfth national conference on Artificial intelligence (vol. 2)
Horn approximations of empirical data
Artificial Intelligence
Pac-learning non-recursive Prolog clauses
Artificial Intelligence
Knowing what doesn't matter: exploiting the omission of irrelevant data
Artificial Intelligence - Special issue on relevance
Optimizing existential datalog queries
Proceedings of the seventh ACM SIGACT-SIGMOD-SIGART symposium on Principles of database systems
Empirical Analysis for Expert Systems
Empirical Analysis for Expert Systems
Algorithmic Program DeBugging
Computers and Intractability; A Guide to the Theory of NP-Completeness
Computers and Intractability; A Guide to the Theory of NP-Completeness
Learning Logical Definitions from Relations
Machine Learning
On the logic of iterated belief revision
TARK '94 Proceedings of the 5th conference on Theoretical aspects of reasoning about knowledge
Estimation of Dependences Based on Empirical Data: Springer Series in Statistics (Springer Series in Statistics)
Efficient distribution-free learning of probabilistic concepts
SFCS '90 Proceedings of the 31st Annual Symposium on Foundations of Computer Science
Pac-learning recursive logic programs: efficient algorithms
Journal of Artificial Intelligence Research
Pac-learning recursive logic programs: negative results
Journal of Artificial Intelligence Research
Revision sequences and nested conditionals
IJCAI'93 Proceedings of the 13th international joint conference on Artifical intelligence - Volume 1
Refinement of uncertain rule bases via reduction
International Journal of Approximate Reasoning
Learning from textbook knowledge: a case study
AAAI'90 Proceedings of the eighth National conference on Artificial intelligence - Volume 2
Reasoning with characteristic models
AAAI'93 Proceedings of the eleventh national conference on Artificial intelligence
The Automated Refinement of a Requirements Domain Theory
Automated Software Engineering
Toward robust real-world inference: a new perspective on explanation-based learning
ECML'06 Proceedings of the 17th European conference on Machine Learning
Hi-index | 0.00 |
A knowledge-based system uses its database (also known as its ''theory'') to produce answers to the queries it receives. Unfortunately, these answers may be incorrect if the underlying theory is faulty. Standard ''theory revision'' systems use a given set of ''labeled queries'' (each a query paired with its correct answer) to transform the given theory, by adding and/or deleting either rules and/or antecedents, into a related theory that is as accurate as possible. After formally defining the theory revision task, this paper provides both sample and computational complexity bounds for this process. It first specifies the number of labeled queries necessary to identify a revised theory whose error is close to minimal with high probability. It then considers the computational complexity of finding this best theory, and proves that, unless P = NP, no polynomial-time algorithm can identify this optimal revision, even given the exact distribution of queries, except in certain simple situations. It also shows that, except in such simple situations, no polynomial-time algorithm can produce a theory whose error is even close to (i.e., within a particular polynomial factor of) optimal. The first (sample complexity) results suggest reasons why theory revision can be more effective than learning from scratch, while the second (computational complexity) results explain many aspects of the standard theory revision systems, including the practice of hill-climbing to a locally-optimal theory, based on a given set of labeled queries.