Stratégies de supervision pour l'apprentissage en-ligne d'un classifieur évolutif de commande gestuelles

Abstract : Touch sensitive interface enable new interaction methods like using gesture commands. To easily memorize more than a dozen of gesture commands, it is important to be able to customize them. The classifier used to recognize drawn symbols must hence be customizable, able to learn from very few data samples, and evolving, able to learn and improve during its use. This work studies several methods of labeling run-time data for the classifier on-line training. We compare seven supervision strategies, depending on user interactions, and system self-evaluation capacities (notion of reject). We show in this paper that the strategy giving the best results is to learn from data implicitly validated by the user, and from data explicitly validated because rejected by the classifier.
Document type :
Conference papers
Complete list of metadatas

Cited literature [9 references]  Display  Hide  Download

https://hal.inria.fr/hal-00968316
Contributor : Manuel Bouillon <>
Submitted on : Monday, March 31, 2014 - 6:07:46 PM
Last modification on : Thursday, February 7, 2019 - 2:20:28 PM
Long-term archiving on : Monday, April 10, 2017 - 7:36:17 AM

File

CIFED_2014_Bouillon_Anquetil.p...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00968316, version 1

Citation

Manuel Bouillon, Eric Anquetil. Stratégies de supervision pour l'apprentissage en-ligne d'un classifieur évolutif de commande gestuelles. Colloque International Francophone sur l'Écrit et le Document (CIFED), Mar 2014, Nancy, France. pp.293--308. ⟨hal-00968316⟩

Share

Metrics

Record views

458

Files downloads

206