Learning Conjunctive Concepts in Structural Domains

Authors:
David Haussler
Affiliations:
Department of Computer Science, University of California, Santa Cruz, CA 95064 USA. HAUSSLER@SATURN.UCSC.EDU
Venue:
Machine Learning
Year:
1989

Citing 0
Cited 43

Learnability and the Vapnik-Chervonenkis dimension

Journal of the ACM (JACM)
On the necessity of Occam algorithms

STOC '90 Proceedings of the twenty-second annual ACM symposium on Theory of computing
Computational learning theory: survey and selected bibliography

STOC '92 Proceedings of the twenty-fourth annual ACM symposium on Theory of computing
Learnability of description logics

COLT '92 Proceedings of the fifth annual workshop on Computational learning theory
Lower bounds for PAC learning with queries

COLT '93 Proceedings of the sixth annual conference on Computational learning theory
CLASSIC learning

COLT '94 Proceedings of the seventh annual conference on Computational learning theory
Inductive logic programming and learnability

ACM SIGART Bulletin
Integrating Multiple Learning Strategies in First Order Logics

Machine Learning - Special issue on multistrategy learning
Learning first order universal Horn expressions

COLT' 98 Proceedings of the eleventh annual conference on Computational learning theory
Prioritizing Information for the Discovery of Phenomena

Journal of Intelligent Information Systems
Learning to Take Actions

Machine Learning
Learning Function-Free Horn Expressions

Machine Learning - The Eleventh Annual Conference on computational Learning Theory
A neuroidal architecture for cognitive computation

Journal of the ACM (JACM)
Mind change complexity of learning logic programs

Theoretical Computer Science
Abstractions for Knowledge Organization of Relational Descriptions

SARA '02 Proceedings of the 4th International Symposium on Abstraction, Reformulation, and Approximation
Mind Change Complexity of Learning Logic Programs

EuroCOLT '99 Proceedings of the 4th European Conference on Computational Learning Theory
Learning Range Restricted Horn Expressions

EuroCOLT '99 Proceedings of the 4th European Conference on Computational Learning Theory
Learning of Class Descriptions from Class Discriminations: A Hybrid Approach for Relational Objects

KI '02 Proceedings of the 25th Annual German Conference on AI: Advances in Artificial Intelligence
Learning Logic Programs with Neural Networks

ILP '01 Proceedings of the 11th International Conference on Inductive Logic Programming
Version spaces and the consistency problem

Artificial Intelligence
Fuzzy lattice reasoning (FLR) classifier and its application for ambient ozone estimation

International Journal of Approximate Reasoning
Connectionist construction of prototypes from decision trees for graph classification

Intelligent Data Analysis
On the connection between the phase transition of the covering test and the learning success rate in ILP

Machine Learning
Extension of the Top-Down Data-Driven Strategy to ILP

Inductive Logic Programming
A Model to Study Phase Transition and Plateaus in Relational Learning

ILP '08 Proceedings of the 18th international conference on Inductive Logic Programming
Knowledge infusion

AAAI'06 proceedings of the 21st national conference on Artificial intelligence - Volume 2
Empirical Study of Relational Learning Algorithms in the Phase Transition Framework

ECML PKDD '09 Proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases: Part I
A formal framework for speedup learning from problems and solutions

Journal of Artificial Intelligence Research
Pac-learning recursive logic programs: negative results

Journal of Artificial Intelligence Research
Learning structural decision trees from examples

IJCAI'91 Proceedings of the 12th international joint conference on Artificial intelligence - Volume 2
Preference elicitation with subjective features

Proceedings of the third ACM conference on Recommender systems
Building theories into instantiation

IJCAI'95 Proceedings of the 14th international joint conference on Artificial intelligence - Volume 2
Propositionalization for clustering symbolic relational descriptions

ILP'02 Proceedings of the 12th international conference on Inductive logic programming
Effective generalization of relational descriptions

AAAI'90 Proceedings of the eighth National conference on Artificial intelligence - Volume 2
Probably approximately correct learning

AAAI'90 Proceedings of the eighth National conference on Artificial intelligence - Volume 2
Version spaces without boundary sets

AAAI'97/IAAI'97 Proceedings of the fourteenth national conference on artificial intelligence and ninth conference on Innovative applications of artificial intelligence
Learning to take actions

AAAI'96 Proceedings of the thirteenth national conference on Artificial intelligence - Volume 1
Learning complex concepts using crowdsourcing: a Bayesian approach

ADT'11 Proceedings of the Second international conference on Algorithmic decision theory
Online closure-based learning of relational theories

ILP'05 Proceedings of the 15th international conference on Inductive Logic Programming
Learning schema mappings

Proceedings of the 15th International Conference on Database Theory
An approach to guided learning of boolean functions

Mathematical and Computer Modelling: An International Journal
Learning and verifying quantified boolean queries by example

Proceedings of the 32nd symposium on Principles of database systems
Learning schema mappings

ACM Transactions on Database Systems (TODS) - Invited papers issue

Quantified Score

Hi-index	0.00

Visualization

Abstract

We study the problem of learning conjunctive concepts from examples on structural domains like the blocks world. This class of concepts is formally defined, and it is shown that even for samples in which each example (positive or negative) is a two-object scene, it is NP-complete to determine if there is any concept in this class that is consistent with the sample. We demonstrate how this result affects the feasibility of Mitchell's version of space approach and how it shows that it is unlikely that this class of concepts is polynomially learnable from random examples alone in the PAC framework of Valiant. On the other hand, we show that for any fixed bound on the number of objects per scene, this class is polynomially learnable if, in addition to providing random examples, we allow the learning algorithm to make subset queries. In establishing this result, we calculate the capacity of the hypothesis space of conjunctive concepts in a structural domain and use a general theorem of Vapnik and Chervonenkis. This latter result can also be used to estimate a sample size sufficient for heuristic learning techniques that do not use queries.