Autonomous Machine Learning - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles ERCIM News Year : 2016

Autonomous Machine Learning

Frédéric Alexandre


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.
Fichier principal
Vignette du fichier
Alexandre_Ercim.pdf (81.44 Ko) Télécharger le fichier
Vignette du fichier
NEDA.pdf (335.31 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Format : Figure, Image
Origin : Files produced by the author(s)

Dates and versions

hal-01401888 , version 1 (23-11-2016)


  • HAL Id : hal-01401888 , version 1


Frédéric Alexandre. Autonomous Machine Learning. ERCIM News, 2016, Special theme: Machine Learning, 107. ⟨hal-01401888⟩
702 View
235 Download


Gmail Facebook X LinkedIn More