Towards Deep Developmental Learning - Archive ouverte HAL Access content directly
Journal Articles IEEE Transactions on Cognitive and Developmental Systems Year : 2016

Towards Deep Developmental Learning

Abstract

Deep learning techniques are having an undeniable impact on general pattern recognition issues. In this paper, from a developmental robotics perspective, we scrutinize deep learning techniques under the light of their capability to construct a hierarchy of meaningful multimodal representations from the raw sensors of robots. These investigations reveal the differences between the methodological constraints of pattern recognition and those of developmental robotics. In particular, we outline the necessity to rely on unsupervised rather than supervised learning methods and we highlight the need for progress towards the implementation of hierarchical predictive processing capabilities. Based on these new tools, we outline the emergence of a new domain that we call deep developmental learning.
Fichier principal
Vignette du fichier
Sigaud_2016_Towards_Deep.pdf (405.68 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01331799 , version 1 (14-06-2016)

Identifiers

Cite

Olivier Sigaud, Alain Droniou. Towards Deep Developmental Learning. IEEE Transactions on Cognitive and Developmental Systems, 2016, 8 (2), pp.99-114. ⟨10.1109/TAMD.2015.2496248⟩. ⟨hal-01331799⟩
140 View
631 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More