Selective reformulation of examples in concept learning (1994) [2 citations — 0 self]

Download:

by Jean-daniel Zucker, Jean-gabriel Ganascia

Proc. of 11 th International Conference on Machine Learning

ftp://ftp.lip6.fr/ibp/reports/laforia.95/laforia.95.08.ps.gz

Add To MetaCart

Popular Tags

No tags have been applied to this document.

BibTeX | Add To MetaCart

@INPROCEEDINGS{Zucker94selectivereformulation,
    author = {Jean-daniel Zucker and Jean-gabriel Ganascia},
    title = {Selective reformulation of examples in concept learning},
    booktitle = {Proc. of 11 th International Conference on Machine Learning},
    year = {1994},
    pages = {352--360},
    publisher = {Morgan Kaufmann}
}

Abstract:

The fundamental tradeoff that is well known in Knowledge Representation and Reasoning affects Concept Learning from Examples too. Representation of learning examples using attribute-value has proved to support efficient inductive algorithms but limited expressiveness whereas more expressive representation languages, typically subsets of First Order Logic (FOL), are supported by less efficient algorithms. In fact, an underlying problem is that of the number of different ways of matching examples, just one in attribute-value representation and potentially large in FOL representation. This paper describes a novel approach to perform representation shifts on learning examples. The structure of these learning examples, initially represented using a subset of FOL-based languages, is reformulated so as to produce new learning examples that are represented using an attribute-value language. What is considered to be an adequate structure varies according to the learning task. We introduce the notion of morion (from the Greek) to qualify this structure and show, through a concrete example, the advantages it offers. We then describe an algorithm which reformulates learning examples automatically and go on to analyze its complexity. This approach to deductive reformulation is implemented in the REMO system that has been experimented on the learning of the construction of Chinese characters.

Citations

2489	Induction of Decision Trees – Quinlan - 1986
747	Learning logical definitions from relations – Quinlan - 1990
625	A theory and methodology of inductive learning – Michalski - 1983
490	Generalization as search – MITCHELL - 1982
371	A further note on inductive generalization – Plotkin - 1971
59	Learning in FOL with a similarity measure – Bisson - 1992
27	Limitations on Inductive Learning – Dietterich - 1989
25	The Need for Constructive Induction – Matheus - 1991
23	Constructive inductive logic programming – Lapointe, Ling, et al. - 1993
20	Introduction: Paradigms for Machine Learning – Carbonell - 1989
17	Incremental adjustment of representations for learning – Schlimmer - 1987
10	CHARADE: A rule System Learning System – Ganascia - 1987
8	Deriving the Learning Bias from Rule Properties – Ganascia - 1991
8	Semantic model for induction of first order theories – ROUVEIROL - 1991
6	An analysis of representation shift in concept learning – Cohen - 1990
4	Representational issues in machine learning – Subramanian - 1989
3	Evaluating alternative instance representations – Saxena - 1989
2	A Mathematical Framework for Studying representation – Holte - 1989
2	Adding Knowledge to SBL through Feature Construction – Matheus - 1991
1	parties des animaux – Aristotle - 1990
1	Pengpeng Z., "Perfectionnement la langue and l'criture chinoises – Bellassen - 1991
1	Czako G., "Induction in an abstraction space: A form of constructive induction – Drastal - 1989
1	Dietterich T., "Selecting Appropriate Representations for Learning from Examples – Flann - 1986
1	Grobelnik M., "Learning nonrecursive definitions of Relations with LINUS – Dzeroski - 1991
1	A Fundamental Tradeoff in Page 10 Knowledge Representation and Reasoning (Final Version – Levesque - 1985
1	Efficient Induction of logic program", in Proceeding of the first conference on algorithmic learning theory – Muggleton - 1990
1	Automating Problem Reformulation", Change of Representation and Inductive Bias – Riddle - 1990
1	A theory of justified reformulation", Change of Representation and Inductive Bias – Subramanian - 1990
1	ed.),"The Concise Oxford Dictionary of Current English – Sikes - 1982
1	Kang Xi Dictionary", The Commercial – Zhang - 1979
1	Principles of Machine Learning – ZhongZhi - 1992
1	Machine Learning Contributions to a Guided Discovery Tutoring Environment for Chinese Characters – Zucker - 1993
1	Ganascia J-G., "Selections and Matches", Rapport Interne du LAFORIA – Zucker - 1994

View or Download | Add to My Collection | Correct Errors