Skip to Main content Skip to Navigation
Poster communications

A Bayesian Experimental Design Approach Maximizing Information Gain for Human-Computer Interaction

Wanyu Liu 1, 2 Rafael Lucas d'Oliveira 3 Michel Beaudouin-Lafon 2 Olivier Rioul 4, 5
1 LTCI - Laboratoire Traitement et Communication de l'Information
2 EX-SITU - Extreme Interaction
Inria Saclay - Ile de France, LRI - Laboratoire de Recherche en Informatique
3 UNICAMP - University of Campinas [Campinas]
4 COMNUM - Communications Numériques
LTCI - Laboratoire Traitement et Communication de l'Information
5 COMELEC - Département Communications & Electronique
Abstract : A new information-theoretic approach based on Bayesian Experimental Design (BED) is applied to human-computer interaction, and in particular to multi-scale navigation. Instead of simply executing user commands, our BIG (Bayesian Information Gain) technique is modeling user behavior and tries to gain information by maximizing the expected mutual information provided by the users' subsequent input.
Document type :
Poster communications
Complete list of metadata
https://hal.inria.fr/hal-01677034
Contributor : Wanyu Liu <>
Submitted on : Sunday, January 7, 2018 - 6:50:50 PM
Last modification on : Friday, October 9, 2020 - 9:44:46 AM

File

Vignette du document
ITA_BIG_v6.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01677034, version 1

Collections

CNRS | INSTITUT-TELECOM | INRIA | CENTRALESUPELEC | UMR8623 | LRI-HCC | PARISTECH | LTCI | COMELEC | COMNUM

Citation

Wanyu Liu, Rafael Lucas d'Oliveira, Michel Beaudouin-Lafon, Olivier Rioul. A Bayesian Experimental Design Approach Maximizing Information Gain for Human-Computer Interaction. ITA 2017 - IEEE Information Theory and Applications Workshop, Feb 2017, San Diego, United States. pp.1. ⟨hal-01677034⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

847

Files downloads

112

 

Contact                    Legal Notice                    Personal Data