Workshops

SMILES: Sensorimotor Interaction, Language and Embodiment of Symbols (full-day)

On the one hand, models of sensorimotor interaction are embodied in the environment and in the interaction with other agents. On the other hand, recent Deep Learning development of Natural Language Processing (NLP) models allow to capture increasing language complexity (e.g. compositional representations, word embedding, long term dependencies). However, those NLP models are disembodied in the sense that they are learned from static datasets of text or speech. How can we bridge the gap from low-level sensorimotor interaction to high-level compositional symbolic communication? The SMILES workshop will address this issue through an interdisciplinary approach involving researchers from (but not limited to):

  • Sensori-motor learning
  • Emergent communication in multi-agent systems
  • Chunking of perceptuomotor gestures
  • Sensori-motor learning
  • Symbol grounding and symbol emergence
  • Compositional representations for communication and action sequence
  • Hierarchical representations of temporal information
  • Language processing and acquisition in brains and machines
  • Models of animal communication
  • Understanding composition and temporal processing in neural network models
  • Enaction, active perception and perception-action loop.
Visit Workshop website

Organizers:

  • Xavier Hinaut, Inria, Bordeaux, France
  • Clément Moulin-Frier, Inria and Ensta ParisTech, Bordeaux, France
  • Silvia Pagliarini, Inria, Bordeaux, France
  • Chukiong Loo, University of Malaya, Kuala Lumpur, Malaysia
  • Michael Spranger, Sony AI and Sony CSL, Tokyo, Japan
  • Tadahiro Taniguchi, Ritsumeikan University, Kyoto, Japan
  • Junpei Zhong, Nottingham Trent University, Nottingham, United Kingdom

This Workshop is scheduled for Sept. 7th, check the schedule

Affective Shared Perception (half-day)

The ability to perceive, understand and respond to social interaction in a human-like manner is one of the most desired skills for artificial agents. These sets of skills are highly complex and dependent on several different research fields, including affective understanding. An agent that can recognize, understand and, most importantly, adapt to different affective reactions from humans can increase its social capabilities by being able to interact and communicate naturally.

Visit Workshop website

Organizers:

  • Pablo Barros, Istituto Italiano di Tecnologia, Genova, Italy
  • Alessandra Sciutti, Istituto Italiano di Tecnologia, Genova, Italy

This Workshop is scheduled for Sept. 7th, check the schedule