Predicting relative performance of classifiers from samples

• Tipo: Artigo em Livro de Atas de Conferência Internacional
• Data: 2005

Autores

Leite, R (Autor) Outra; Pavel Brazdil (Autor) FEP

Ata de Conferência Internacional

Título: ICML 2005 - Proceedings of the 22nd International Conference on Machine Learning

Páginas: 497-504

ICML 2005: 22nd International Conference on Machine Learning

Bonn, 7 August 2005 through 11 August 2005

Indexação

Scopus - 40 Citações

Outras Informações

ID Authenticus: P-007-EY7

DOI: 10.1145/1102351.1102414

Abstract (EN): This paper is concerned with the problem of predicting relative performance of classification algorithms. It focusses on methods that use results on small samples and discusses the shortcomings of previous approaches. A new variant is proposed that exploits, as some previous approaches, meta-learning. The method requires that experiments be conducted on few samples. The information gathered is used to identify the nearest learning curve for which the sampling procedure was carried out fully. This in turn permits to generate a prediction regards the relative performance of algorithms. Experimental evaluation shows that the method competes well with previous approaches and provides quite good and practical solution to this problem.

Idioma: Inglês

Tipo (Avaliação Docente): Científica