A bio-inspired model towards vocal gesture learning in songbird - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2018

A bio-inspired model towards vocal gesture learning in songbird

Silvia Pagliarini
Xavier Hinaut

Résumé

The paper proposes a bio-inspired model for an imitative sensorimotor learning, which aims at building a map between the sensory representations of gestures (sensory targets) and their underlying motor pattern through random exploration of the motor space. An example of such learning process occurs during vocal learning in humans or birds, when young subjects babble and learn to copy previously heard adult vocalizations. Previous work has suggested that a simple Hebbian learning rule allows perfect imitation when sensory feedback is a purely linear function of the motor pattern underlying movement production. We aim at generalizing this model to the more realistic case where sensory responses are sparse and non-linear. To this end, we explore the performance of various learning rules and nor-malizations and discuss their biological relevance. Importantly, the proposed model is robust whatever normalization is chosen. We show that both the imitation quality and the convergence time are highly dependent on the sensory selectivity and dimension of the motor representation.
Fichier principal
Vignette du fichier
Pagliarini2018_ICDL_HAL-v2.pdf (1.26 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-01906459 , version 1 (26-10-2018)
hal-01906459 , version 2 (22-04-2021)

Identifiants

  • HAL Id : hal-01906459 , version 2

Citer

Silvia Pagliarini, Xavier Hinaut, Arthur Leblois. A bio-inspired model towards vocal gesture learning in songbird. 2018 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob), Sep 2018, Tokyo, Japan. ⟨hal-01906459v2⟩
210 Consultations
200 Téléchargements

Partager

Gmail Facebook X LinkedIn More