On data and algorithms: Understanding inductive performance

• Tipo: Artigo em Revista Científica Internacional
• Data: 2004

Autores

Alexandre Kalousis (Autor) Outra; João Gama (Autor) FEP; Melanie Hilario (Autor) Outra

Revista

Título: Machine Learning

Vol. 54 Nº 3

Páginas: 275-312

ISSN: 0885-6125

Editora: Springer Nature

Indexação

ISI Web of Knowledge - 47 Citações

ISI Web of Science - 37 Citações

Scopus - 68 Citações

Classificação Científica

FOS: Ciências exactas e naturais

CORDIS: Ciências Físicas > Ciência de computadores

Outras Informações

ID Authenticus: P-000-BFK

DOI: 10.1023/b:mach.0000015882.38031.85

Abstract (EN): In this paper we address two symmetrical issues, the discovery of similarities among classification algorithms, and among datasets. Both on the basis of error measures, which we use to define the error correlation between two algorithms, and determine the relative performance of a list of algorithms. We use the first to discover similarities between learners, and both of them to discover similarities between datasets. The latter sketch maps on the dataset space. Regions within each map exhibit specific patterns of error correlation or relative performance. To acquire an understanding of the factors determining these regions we describe them using simple characteristics of the datasets. Descriptions of each region are given in terms of the distributions of dataset characteristics within it.

Idioma: Inglês

Tipo (Avaliação Docente): Científica

Nº de páginas: 38