Skip to Main content Skip to Navigation
Conference papers

How to optimize sample in active learning: Dispersion, an optimum criterion for classification ?

Abstract : We want generate learning data appropriated to classification problems. First, we show that theorical results about low discrepancy sequences in regression problems are not adequate for classification problems. Then, we show with theorical and experimental arguments that minimising the dispersion of the sample is a relevant strategy to optimize performance of classification learning.
Document type :
Conference papers
Complete list of metadata

https://hal.inrae.fr/hal-02591892
Contributor : Migration Irstea Publications <>
Submitted on : Friday, May 15, 2020 - 3:35:37 PM
Last modification on : Tuesday, March 23, 2021 - 5:22:03 PM

Identifiers

  • HAL Id : hal-02591892, version 1
  • IRSTEA : PUB00026365

Collections

Citation

Benoît Gandar, G. Loosli, Guillaume Deffuant. How to optimize sample in active learning: Dispersion, an optimum criterion for classification ?. ENBIS (European Network for Business and Industrial Statistics), Jul 2009, Saint-Etienne, France. ⟨hal-02591892⟩

Share

Metrics

Record views

21