Brave induction: a logical framework for learning from incomplete information

Authors:
Chiaki Sakama;Katsumi Inoue
Affiliations:
Department of Computer and Communication Sciences, Wakayama University, Wakayama, Japan 640-8510;National Institute of Informatics, Tokyo, Japan 101-8430
Venue:
Machine Learning
Year:
2009

Citing 18
Cited 2

Saturation, nonmonotonic reasoning and the closed-world assumption

Artificial Intelligence
On the relationship between circumscription and negation as failure

Artificial Intelligence
Induction as nonmonotonic inference

Proceedings of the first international conference on Principles of knowledge representation and reasoning
Linear resolution for consequence finding

Artificial Intelligence
Clausal Discovery

Machine Learning - special issue on inductive logic programming
Logical settings for concept-learning

Artificial Intelligence
Abduction from logic program: semantics and complexity

Theoretical Computer Science
Nonmonotonic Logic II: Nonmonotonic Modal Theories

Journal of the ACM (JACM)
Foundations of Inductive Logic Programming

Foundations of Inductive Logic Programming
Answer set programming and plan generation

Artificial Intelligence
Automated Abduction

Computational Logic: Logic Programming and Beyond, Essays in Honour of Robert A. Kowalski, Part II
The Many Faces of Inductive Logic Programming

ISMIS '93 Proceedings of the 7th International Symposium on Methodologies for Intelligent Systems
On Indefinite Databases and the Closed World Assumption

Proceedings of the 6th Conference on Automated Deduction
Induction as Consequence Finding

Machine Learning
Rationality postulates for induction

TARK '96 Proceedings of the 6th conference on Theoretical aspects of rationality and knowledge
Induction from answer sets in nonmonotonic logic programs

ACM Transactions on Computational Logic (TOCL)
Application of abductive ILP to learning metabolic network inhibition from temporal data

Machine Learning
Logic programs with monotone abstract constraint atoms*

Theory and Practice of Logic Programming

Exploring relations between answer set programs

Logic programming, knowledge representation, and nonmonotonic reasoning
Integrating model checking and inductive logic programming

ILP'11 Proceedings of the 21st international conference on Inductive Logic Programming

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper introduces a novel logical framework for concept-learning called brave induction. Brave induction uses brave inference for induction and is useful for learning from incomplete information. Brave induction is weaker than explanatory induction which is normally used in inductive logic programming, and is stronger than learning from satisfiability, a general setting of concept-learning in clausal logic. We first investigate formal properties of brave induction, then develop an algorithm for computing hypotheses in full clausal theories. Next we extend the framework to induction in nonmonotonic logic programs. We analyze computational complexity of decision problems for induction on propositional theories. Further, we provide examples of problem solving by brave induction in systems biology, requirement engineering, and multiagent negotiation.