[robotics-worldwide] [meetings] Call for Participation : Workshop on Continual Unsupervised Sensorimotor Learning - Tokyo - September 17th

classic Classic list List threaded Threaded
1 message Options
Reply | Threaded
Open this post in threaded view
|

[robotics-worldwide] [meetings] Call for Participation : Workshop on Continual Unsupervised Sensorimotor Learning - Tokyo - September 17th

Nguyen, Sao Mai
Call for Participation

Workshop on Continual Unsupervised Sensorimotor Learning at IEEE
ICDL-Epirob 2018 - Tokyo - September 17th

Website : https://urldefense.proofpoint.com/v2/url?u=http-3A__conferences.au.dk_icdl-2Depirob-2D2018-2Dworkshop_&d=DwIFaQ&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=0w3solp5fswiyWF2RL6rSs8MCeFamFEPafDTOhgTfYI&m=X_rh0Dp7iaJobF8XNM_qF6y62PlyGydlL96oiXzO-gM&s=6SUePBp-fvjWhTxvux2vLSez70crsvPOdSkOrqzXPhc&e=
============================================================


Invited Speakers

   -

   Jochen Triesch, Frankfurt Institute of Advanced Studies, Germany
   -

   David Ha, Google Brain
   - Lorenzo Jamone, Queen Mary University of London, UK



Scope

As the algorithms for learning single tasks in restricted environments are
improving, new challenges have gained relevance. They include multi-task
learning, multimodal sensorimotor learning in open worlds and lifelong
adaptation to injury, growth and ageing.


In this workshop we will discuss the developmental processes involved in
the emergence of representations of action and perception in humans and
artificial agents in continual learning. These processes include
action-perception cycle, active perception, continual sensory-motor learning,
environmental-driven scaffolding, and intrinsic motivation.

The discussion will be strongly motivated by behavioural and neural data.
We hope to provide a discussion friendly environment to connect with
research with similar interest regardless of their area of expertise which
could include robotics, computer science, psychology, neuroscience, etc. We
would also like to devise a roadmap or strategies to develop mathematical
and computational models to improve robot performance and/or to attempt to
unveil the underlying mechanisms that lead to continual adaptation to
changing environment or embodiment and continual learning in open-ended
environments.

The primary list of topics covers the following (but not limited to):

   -

   Emergence of representations via continual interaction
   -

   Continual sensory-motor learning
   -

   Action-perception cycle
   -

   Active perception
   -

   Environmental-driven scaffolding
   -

   Intrinsic motivation
   -

   Neural substrates, neural circuits and neural plasticity
   -

   Human and animal behaviour experiments and models
   -

   Reinforcement learning and deep reinforcement learning for life-long
   learning
   -

   Multisensory robot learning
   -

   Multimodal sensorimotor learning
   -

   Affordance learning
   -

   Prediction learning



Organizers:

   -

   Nicolás Navarro-Guerrero, Aarhus University, Aarhus, Denmark
   -

   Sao Mai Nguyen, IMT Atlantique, France
   -

   Erhan Öztop, Özyeğin University, Turkey
   -

   Junpei Zhong, National Institute of Advanced Industrial Science and
   Technology (AIST), Japan





Nguyen Sao Mai
[hidden email]
Researcher in Cognitive Developmental Robotics
https://urldefense.proofpoint.com/v2/url?u=http-3A__nguyensmai.free.fr&d=DwIFaQ&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=0w3solp5fswiyWF2RL6rSs8MCeFamFEPafDTOhgTfYI&m=X_rh0Dp7iaJobF8XNM_qF6y62PlyGydlL96oiXzO-gM&s=uRJself0Fvn7jgM7uginjjY41KWoYUulklpVc0Qz33Q&e=
_______________________________________________
robotics-worldwide mailing list
[hidden email]
http://duerer.usc.edu/mailman/listinfo.cgi/robotics-worldwide