A bio-inspired model towards vocal gesture learning in songbird

被引:0
|
作者
Pagliarini, Silvia [1 ,2 ]
Hinaut, Xavier [1 ,2 ]
Leblois, Arthur [3 ]
机构
[1] Inria Bordeaux Sud Ouest, Talence, France
[2] Univ Bordeaux, Bordeaux INP, CNRS, LaBRI,UMR 5800,IMN,UMR 5293, Bordeaux, France
[3] Univ Bordeaux, CNRS, IMN, UMR 5293, Bordeaux, France
关键词
MIRROR NEURONS; MECHANISMS; IMITATION; BIRDSONG;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
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 normalizations 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.
引用
收藏
页码:269 / 274
页数:6
相关论文
共 50 条
  • [1] Towards a Predictive Bio-Inspired Navigation Model
    Gay, Simon
    Le Run, Kevin
    Pissaloux, Edwige
    Romeo, Katerine
    Lecomte, Christele
    [J]. INFORMATION, 2021, 12 (03) : 1 - 19
  • [2] Bayesian Bio-inspired Model for Learning Interactive Trajectories
    Dore, Alessio
    Regazzoni, Carlo S.
    [J]. AVSS: 2009 6TH IEEE INTERNATIONAL CONFERENCE ON ADVANCED VIDEO AND SIGNAL BASED SURVEILLANCE, 2009, : 207 - 212
  • [3] Bio-inspired cognitive model of motor learning by imitation
    Machaen, Zandor
    Martin, Luis
    Rosales, Jonathan-Hernando
    [J]. COGNITIVE SYSTEMS RESEARCH, 2021, 66 : 134 - 149
  • [4] Bio-inspired Deep Learning Model for Object Recognition
    Charalampous, Konstantinos
    Gasteratos, Antonios
    [J]. 2013 IEEE INTERNATIONAL CONFERENCE ON IMAGING SYSTEMS AND TECHNIQUES (IST 2013), 2013, : 51 - 55
  • [5] Bio-inspired model of robot adaptive learning and mapping
    Ramirez, Alejandra Barrera
    Ridel, Alfredo Weitzenfeld
    [J]. 2006 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS, VOLS 1-12, 2006, : 4750 - +
  • [6] Bio-inspired system for gesture imitation applied in robotics
    Nope, Sandra E.
    [J]. INGENIERIA Y COMPETITIVIDAD, 2013, 15 (02): : 57 - 67
  • [7] Towards a bio-inspired soft chemistry
    Livage, Jacques
    [J]. ACTUALITE CHIMIQUE, 2011, (348-49): : 64 - 69
  • [8] Bio-Inspired Deep Attribute Learning Towards Facial Aesthetic Prediction
    Xu, Mingliang
    Chen, Fuhai
    Li, Lu
    Shen, Chen
    Lv, Pei
    Zhou, Bing
    Ji, Rongrong
    [J]. IEEE TRANSACTIONS ON AFFECTIVE COMPUTING, 2021, 12 (01) : 227 - 238
  • [9] Analysis of a Soft Bio-Inspired Active Actuation Model for the Design of Artificial Vocal Folds
    Shariati, Azadeh
    Wurdemann, Helge A.
    [J]. JOURNAL OF MECHANISMS AND ROBOTICS-TRANSACTIONS OF THE ASME, 2023, 15 (03):
  • [10] Towards a bio-inspired design of a photovoltaic facade
    Assoa, Ya Brigitte
    Ratovonkery, Julie
    Menezo, Christophe
    Morlot, Rodolphe
    [J]. RENEWABLE ENERGY, 2024, 229