A critique of the valiant model

Authors:
Wray Buntine
Affiliations:
Key Centre for Advanced Computing Sciences, University of Technology, Sydney, Australia
Venue:
IJCAI'89 Proceedings of the 11th international joint conference on Artificial intelligence - Volume 1
Year:
1989

Citing 11
Cited 1

A theory of the learnable

Communications of the ACM
Occam's razor

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

Artificial Intelligence
Learning classification rules using Bayes

Proceedings of the sixth international workshop on Machine learning
Interactive induction

Machine intelligence 12
Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference

Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference
Learning Decision Lists

Machine Learning
Induction of Decision Trees

Machine Learning
Learning Quickly When Irrelevant Attributes Abound: A New Linear-Threshold Algorithm

Machine Learning
Learning From Noisy Examples

Machine Learning
Handbook of Mathematical Functions, With Formulas, Graphs, and Mathematical Tables,

Handbook of Mathematical Functions, With Formulas, Graphs, and Mathematical Tables,

Random Case Analysis of Inductive Learning Algorithms

DS '98 Proceedings of the First International Conference on Discovery Science

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper considers the Valiant framework as it is applied to the task of learning logical concepts from random examples. It is argued that the current interpretation of this Valiant model departs from common sense and practical experience in a number of ways: it does not allow sample dependent bounds, it uses a worst case rather than an average case analysis, and it does not accommodate preferences about hypotheses. It is claimed that as a result, the current model can produce overlyconservative estimates of confidence and can fail to model the logical induction process as it is often implemented. A Bayesian approach is developed, based on the sample dependent notion of disagreement between consistent hypotheses. This approach seems to overcome the indicated problems.