[robotics-worldwide] [meetings] ICML Workshop on Machine Learning for Interactive Systems and Robots

Heriberto Cuayahuitl h.cuayahuitl at gmail.com
Sun Apr 5 04:20:04 PDT 2015

ICML Workshop on Machine Learning for Interactive Systems and Robots

July 11, 2015, Lille, France


Call for Papers

Learning systems or robots that interact with their environment by
perceiving, acting or communicating often face a challenge in how
to bring these different concepts together. This challenge arises
because core concepts are typically studied within their respective
communities, such as the computer vision, robotics and natural
language processing communities, among others. Building a bridge
across communities is highly important for practical applications
in robotics, human-robot interaction and intelligent interfaces.
Equally important, it encourages basic and applied advances in
research on adaptive sensorimotor, perception-action and perception-
communication loops in general cognition, and also encourages research
on novel ways for training systems from interaction with people in
their physical environments to form generally intelligent systems.

Machine learning topics include, but are not limited to:
- Reinforcement learning (direct and inverse)
- Supervised learning
- Unsupervised learning
- Active learning
- Multi-task and transfer learning
- Learning from human feedback
- Learning from teaching, tutoring, instruction and demonstration
- Combinations or generalisations of the above

Interactive systems using machine learning include, but are not limited to:
- (Socially) Interactive robots
- Embodied virtual agents
- Avatars
- Multimodal systems
- Cognitive (robotics) architectures
- Spoken dialogue systems

Types of communication include, but are not limited to:
- System interacting with a single human user
- System interacting multiple human users
- System interacting with the environment
- System interacting with other machines

Submissions can take two forms. Long papers should not exceed 8 pages,
and short papers should not exceed 4 pages -- both excluding references.
Position papers of either length are also welcome. All papers should
follow the JMLR format: https://mlis-workshop.org/2015/format.tar.gz

Submissions should be made through the following EasyChair link:

Accepted papers will be published in the JMLR Workshop & Conference

Overviews of machine learning topics for interactive system can be found

Invited Speakers:
Juergen Schmidhuber (tbc), IDSIA, Switzerland
Ruslan Salakhutdinov, University of Toronto, Canada
Bjoern Schuller, Imperial College, United Kingdom
Ashutosh Saxena, Cornell University, United States

Important Dates:
May 1, Paper due date
May 10, Notification of acceptance
May 24, Camera-ready deadline
July 10-11, MLIS'15 Workshop

Organising Committee:
Heriberto Cuayáhuitl, Heriot-Watt University, Edinburgh, UK
Nina Dethlefs, University of Hull, UK
Lutz Frommberger, University of Bremen, Germany
Martijn van Otterlo, Radboud University Nijmegen, The Netherlands
Olivier Pietquin, University Lille 1, France

Contact: organizers at mlis-workshop.org

More information about the robotics-worldwide mailing list