Autonomous Machine Learning

Frédéric Alexandre 1
1 Mnemosyne - Mnemonic Synergy
LaBRI - Laboratoire Bordelais de Recherche en Informatique, Inria Bordeaux - Sud-Ouest, IMN - Institut des Maladies Neurodégénératives [Bordeaux]
Abstract : Inspiration from human learning sets the focus on one essential but poorly studied characteristic of learning: Autonomy. One remarkable characteristic of human learning is that, whereas we are in general not excellent in one specific domain, we are quite good in most of them, and able to adapt when a new problem appears. We are versatile and adaptable, which are critical properties for autonomous learning: we can learn in a changing and uncertain world. With neither explicit labels, nor data preprocessing or segmentation, we are able to pay attention to important information and neglect noise. We define by ourselves our goals and the means to reach them, self-evaluate our performances and re-exploit previously learned knowledge and strategies in some different context. In contrast, recent advances in Machine Learning exhibit impressive results, with powerful algorithms surpassing human performances in some very specific domains of expertise, but these models still have very poor autonomy.
Type de document :
Article dans une revue
ERCIM News, ERCIM, 2016, Special theme: Machine Learning
Liste complète des métadonnées
Contributeur : Frédéric Alexandre <>
Soumis le : mercredi 23 novembre 2016 - 22:25:02
Dernière modification le : jeudi 11 janvier 2018 - 06:24:26
Document(s) archivé(s) le : mardi 21 mars 2017 - 00:03:09


Fichiers produits par l'(les) auteur(s)


  • HAL Id : hal-01401888, version 1


Frédéric Alexandre. Autonomous Machine Learning. ERCIM News, ERCIM, 2016, Special theme: Machine Learning. 〈hal-01401888〉



Consultations de la notice


Téléchargements de fichiers