---
title: "Empirical Bias for Version Space"
authors:
  - "Jacques Nicolas"
doi: ""
url: "https://ijcai.org/proceedings/1991/98"
pdf: "https://ijcai.org/proceedings/1991/0098.pdf"
venue: "Proceedings of the Twelfth International Joint Conference on Artificial Intelligence"
year: 1991
pages: "671-676"
track: "Learning Be Knowledge Acquisition"
keywords:
---

# Empirical Bias for Version Space

Jacques Nicolas

*Proceedings of the Twelfth International Joint Conference on Artificial Intelligence*, pages 671-676.

## Abstract

The ability to generalize remains one of the central issues of concept learning. A general generalization algorithm -the Candidate Elimination Algorithmexists but practical applications of this algorithm are still limited, due to its low convergence. The issue has shifted to the design of a useful "bias" limiting the size of the Version Space. This paper proposes a new kind of bias, called empirical bias, and a new general algorithm, ICE, for generalization in presence of bias. This proposition is founded on the concept of focus set, which provides a very flexible way to express expectations or constraints on the space of generalizations.