Reservoir SMILES: Towards SensoriMotor Interaction of Language and Embodiment of Symbols with Reservoir Architectures - TEL - Thèses en ligne Access content directly
Habilitation À Diriger Des Recherches Year : 2022

Reservoir SMILES: Towards SensoriMotor Interaction of Language and Embodiment of Symbols with Reservoir Architectures

Xavier Hinaut

Abstract

Language involves several hierarchical levels of abstraction. Most models focus on a particular level of abstraction making them unable to model bottom-up and top-down processes. Moreover, we do not know how the brain grounds symbols to perceptions and how these symbols emerge throughout development. Experimental evidence suggests that perception and action shape one-another (e.g. motor areas activated during speech perception) but the precise mechanisms involved in this action-perception shaping at various levels of abstraction are still largely unknown. My previous and current work include the modelling of language comprehension, language acquisition with a robotic perspective, sensorimotor models and extended models of Reservoir Computing to model working memory and hierarchical processing. I propose to create a new generation of neural-based computational models of language processing and production; to use biologically plausible learning mechanisms relying on recurrent neural networks; create novel sensorimotor mechanisms to account for action-perception shaping; build hierarchical models from sensorimotor to sentence level; embody such models in robots.
Fichier principal
Vignette du fichier
Hinaut2022_HDR_Habilitation-Thesis_HAL-v1.pdf (5.18 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

tel-03946773 , version 1 (19-01-2023)

Identifiers

  • HAL Id : tel-03946773 , version 1

Cite

Xavier Hinaut. Reservoir SMILES: Towards SensoriMotor Interaction of Language and Embodiment of Symbols with Reservoir Architectures. Artificial Intelligence [cs.AI]. Université de Bordeaux (UB), France, 2022. ⟨tel-03946773⟩
83 View
128 Download

Share

Gmail Facebook X LinkedIn More