(Agnostic) PAC learning concepts in higher-order logic

Authors:
K. S. Ng
Affiliations:
Symbolic Machine Learning and Knowledge Acquisition, National ICT Australia Limited
Venue:
ECML'06 Proceedings of the 17th European conference on Machine Learning
Year:
2006

Citing 10
Cited 1

Inductive logic programming and learnability

ACM SIGART Bulletin
Grammatically biased learning: learning logic programs using an explicit antecedent description language

Artificial Intelligence
First-order jk-clausal theories are PAC-learnable

Artificial Intelligence
Logical settings for concept-learning

Artificial Intelligence
On the boosting ability of top-down decision tree learning algorithms

Journal of Computer and System Sciences
Learning in Neural Networks: Theoretical Foundations

Learning in Neural Networks: Theoretical Foundations
Propositionalization approaches to relational data mining

Relational Data Mining
Learning Decision Lists

Machine Learning
Logic and Learning

Logic and Learning
Generalization behaviour of alkemic decision trees

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

Learning Modal Theories

Inductive Logic Programming

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper studies the PAC and agnostic PAC learnability of some standard function classes in the learning in higher-order logic setting introduced by Lloyd et al. In particular, it is shown that the similarity between learning in higher-order logic and traditional attribute-value learning allows many results from computational learning theory to be ‘ported' to the logical setting with ease. As a direct consequence, a number of non-trivial results in the higher-order setting can be established with straightforward proofs. Our satisfyingly simple analysis provides another case for a more in-depth study and wider uptake of the proposed higher-order logic approach to symbolic machine learning.