Version spaces without boundary sets

Authors:
Haym Hirsh;Nina Mishra;Leonard Pitt
Affiliations:
Computer Science Department, Rutgers University, New Brunswick, NJ;Computer Science Department, University of Illinois at Urbana, Urbana, IL;Computer Science Department, University of Illinois at Urbana, Urbana, IL
Venue:
AAAI'97/IAAI'97 Proceedings of the fourteenth national conference on artificial intelligence and ninth conference on Innovative applications of artificial intelligence
Year:
1997

Citing 15
Cited 11

Machine learning of inductive bias

Machine learning of inductive bias
Occam's razor

Information Processing Letters
On generating all maximal independent sets

Information Processing Letters
Quantifying inductive bias: AI learning algorithms and Valiant's learning framework

Artificial Intelligence
Computational limitations on learning from examples

Journal of the ACM (JACM)
Learnability and the Vapnik-Chervonenkis dimension

Journal of the ACM (JACM)
Generalizing Version Spaces

Machine Learning
On the Learnability of Disjunctive Normal Form Formulas

Machine Learning
Identifying the Minimal Transversals of a Hypergraph and Related Problems

SIAM Journal on Computing
On the complexity of dualization of monotone disjunctive normal forms

Journal of Algorithms
Complexity theoretic hardness results for query learning

Computational Complexity
Learning Conjunctive Concepts in Structural Domains

Machine Learning
Learning Decision Lists

Machine Learning
A Version Space Approach to Learning Context-free Grammars

Machine Learning
Theoretical underpinnings of version spaces

IJCAI'91 Proceedings of the 12th international joint conference on Artificial intelligence - Volume 2

Generating all maximal independent sets of bounded-degree hypergraphs

COLT '97 Proceedings of the tenth annual conference on Computational learning theory
Efficient Read-Restricted Monotone CNF/DNF Dualization by Learning with Membership Queries

Machine Learning
Machine Learning on the Basis of Formal Concept Analysis

Automation and Remote Control
Efficient Instance Retraction

AIMSA '02 Proceedings of the 10th International Conference on Artificial Intelligence: Methodology, Systems, and Applications
Concept Learning with Approximation: Rough Version Spaces

TSCTC '02 Proceedings of the Third International Conference on Rough Sets and Current Trends in Computing
Version Space Learning with DNA Molecules

DNA8 Revised Papers from the 8th International Workshop on DNA Based Computers: DNA Computing
Programming by Demonstration Using Version Space Algebra

Machine Learning
A Unifying Version-Space Representation

Annals of Mathematics and Artificial Intelligence
Learning approximate preconditions for methods in hierarchical plans

ICML '05 Proceedings of the 22nd international conference on Machine learning
Learning to identify student preconceptions from text

HLT-NAACL-EDUC '03 Proceedings of the HLT-NAACL 03 workshop on Building educational applications using natural language processing - Volume 2
A SAT-based version space algorithm for acquiring constraint satisfaction problems

ECML'05 Proceedings of the 16th European conference on Machine Learning

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper shows that it is not necessary to maintain boundary sets to reason using version spaces. Rather, most of the operations typically performed on version spaces for a concept class can be tractably executed directly on the training data, as long as it is tractable to solve the consistency problem for that concept class -- to determine whether there exists any concept in the concept class that correctly classifies the data. The equivalence of version-space learning to the consistency problem bridges a gap between empirical and theoretical approaches to machine learning, since the consistency problem is already known to be critical to learning in the PAC (Probably Approximately Correct) sense. By exhibiting this link to the consistency problem, we broaden the class of problems to which version spaces can be applied to include concept classes where boundary sets can have exponential or infinite size and cases where boundary sets are not even well defined.