Programming by Feedback - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2014

Programming by Feedback

Abstract

This paper advocates a new ML-based programming framework, called Programming by Feedback (PF), which involves a sequence of interactions between the active computer and the user. The latter only provides preference judgments on pairs of solutions supplied by the active computer. The active computer involves one learning and one optimization components; the learning component estimates the user's utility function and accounts for the user's (possibly limited) competence; the optimization component explores the search space and returns the most appropriate candidate solution. A proof of principle of the approach is proposed, showing that PF requires a handful of interactions in order to solve some discrete and continuous benchmark problems.
Fichier principal
Vignette du fichier
programming_by_feedback.pdf (258.55 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00980839 , version 1 (22-04-2014)

Identifiers

  • HAL Id : hal-00980839 , version 1

Cite

Riad Akrour, Marc Schoenauer, Michèle Sebag, Jean-Christophe Souplet. Programming by Feedback. International Conference on Machine Learning, Jun 2014, Pékin, China. pp.1503-1511. ⟨hal-00980839⟩
2031 View
741 Download

Share

Gmail Facebook X LinkedIn More