[robotics-worldwide] [meetings] Call for abstracts for the NIPS 2016 workshop on Neurorobotics

Elmar Rueckert elmar at robot-learning.de
Tue Oct 25 05:35:00 PDT 2016


We apologize if you received multiple copies of this letter.
Please feel free to distribute it to those who might be interested.

************************************************************
*****************
Call for participation in the workshop on

*Neurorobotics: a chance for new ideas, algorithms and approaches*
Dec 9-10, Barcelona, Spain,
Link: https://urldefense.proofpoint.com/v2/url?u=http-3A__www.neurorobotic.eu&d=DQIFaQ&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=0w3solp5fswiyWF2RL6rSs8MCeFamFEPafDTOhgTfYI&m=Ws87Rfj9nRE8muIQBmBMqS2czEcteBUkP8L6FT117jc&s=_vl8Ub0mjGqkhMcgW298QqaJdGT8Cb79JgB_i1UmAYA&e= 
<https://urldefense.proofpoint.com/v2/url?u=http-3A__www.neurorobotic.eu&d=DQMFaQ&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=0w3solp5fswiyWF2RL6rSs8MCeFamFEPafDTOhgTfYI&m=TF10pJvxPx0d5tIbb6Z-MXny9--ST4L8sxQ9q6rZB0E&s=apH4vQTLtTHTmU3hVBM-nfAPs8p51OikqzogNLlDHXQ&e=>

at the conference

*NIPS 2016*
Monday December 05 -- Saturday December 10, 2016
Centre Convencions Internacional Barcelona, Barcelona SPAIN
Link: https://urldefense.proofpoint.com/v2/url?u=http-3A__www.nips.cc&d=DQIFaQ&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=0w3solp5fswiyWF2RL6rSs8MCeFamFEPafDTOhgTfYI&m=Ws87Rfj9nRE8muIQBmBMqS2czEcteBUkP8L6FT117jc&s=BweG55ab7b1Mk-vDc0zngHMkUyF-mO0DuZOBxwdNntg&e= 
<https://urldefense.proofpoint.com/v2/url?u=http-3A__www.nips.cc&d=DQMFaQ&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=0w3solp5fswiyWF2RL6rSs8MCeFamFEPafDTOhgTfYI&m=TF10pJvxPx0d5tIbb6Z-MXny9--ST4L8sxQ9q6rZB0E&s=nEhd5CB8uZsjW4SAHAJ1MNE2YgHmHMH3knp3muJYwcU&e=>

************************************************************
*****************

**** List of Speakers ****

→ Pieter Abbeel (University of California, Berkeley)
→ Jan Babic (Josef Stefan Institute Ljubijana)
→ Johanni Brea  (École polytechnique fédérale de Lausanne, EPFL)
→ Sylvain Calinon (Idiap Research Institute, EPFL Lausanne)
→ Tobi Delbrück  (University of Zurich and ETH Zurich)
→ Chelsea Finn  (University of California, Berkeley)
→ Martin Giese (University Clinic Tübingen)
→ Moritz Grosse-Wentrup (Max Planck Institute Tuebingen)
→ Frank Hutter (University Freiburg)
→ Bert Kappen (Radboud University)
→ Kristian Kersting (Technische Universität Dortmund)
→ Robert Legenstein (Graz University of Technology)
→ Sergey Levine (University of California, Berkeley)
→ Jean-Pascal Pfister  (University of Zurich and ETH Zurich)
→ Juergen Schmidhuber (Scientific Director of the Swiss AI Lab IDSIA)
→ Paul Schrater (University of Minnesota)
→ Peter Stone (University of Texas at Austin)
→ Richard Sutton (University of Alberta)
→ Emo Todorov (University of Washington)

**** Organizer ****

→ Elmar Rueckert (Technische Universitaet Darmstadt, Germany)
→ Martin Riedmiller (Google DeepMind)

**** Important Dates ****

Paper Submission Deadline: November 19th, 2016
Notification of acceptance: November 30th, 2016
Workshop day: December 9th, 2016

**** Format ****
We invite submissions in the form of abstracts of *up to two pages
excluding references *following NIPS formatting guidelines.

The abstracts will be reviewed by experts in fields of machine learning,
neuroscience, robotics and prosthetics. Accepted contributions will be
featured in a *poster session* and will be included in the *workshop
proceedings*, which will be available at the workshop website.

We encourage work-in-progress to be submitted and will take this into
account in the review process. Submit at
*https://urldefense.proofpoint.com/v2/url?u=https-3A__easychair.org_conferences_-3Fconf-3Dnips2016workshopneur&d=DQIFaQ&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=0w3solp5fswiyWF2RL6rSs8MCeFamFEPafDTOhgTfYI&m=Ws87Rfj9nRE8muIQBmBMqS2czEcteBUkP8L6FT117jc&s=_BFXLlnhYG96JWq9hAf6_SsL5M3aO-xOonAKjh0TWlg&e= 
<https://urldefense.proofpoint.com/v2/url?u=https-3A__easychair.org_conferences_-3Fconf-3Dnips2016workshopneur&d=DQMFaQ&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=0w3solp5fswiyWF2RL6rSs8MCeFamFEPafDTOhgTfYI&m=TF10pJvxPx0d5tIbb6Z-MXny9--ST4L8sxQ9q6rZB0E&s=Wgmp4COfq4edlhQmzdvy8nUo4eIx0l9FuvT0hjH69ug&e=>
*
Questions should be directed to *rueckert.elmar at gmail.com
<rueckert.elmar at gmail.com>*.


**** Topics and Details ****

taken from https://urldefense.proofpoint.com/v2/url?u=http-3A__www.neurorobotic.eu&d=DQIFaQ&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=0w3solp5fswiyWF2RL6rSs8MCeFamFEPafDTOhgTfYI&m=Ws87Rfj9nRE8muIQBmBMqS2czEcteBUkP8L6FT117jc&s=_vl8Ub0mjGqkhMcgW298QqaJdGT8Cb79JgB_i1UmAYA&e= 
<https://urldefense.proofpoint.com/v2/url?u=http-3A__www.neurorobotic.eu&d=DQMFaQ&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=0w3solp5fswiyWF2RL6rSs8MCeFamFEPafDTOhgTfYI&m=TF10pJvxPx0d5tIbb6Z-MXny9--ST4L8sxQ9q6rZB0E&s=apH4vQTLtTHTmU3hVBM-nfAPs8p51OikqzogNLlDHXQ&e=>

  Title: Neurorobotics: A chance for new ideas, algorithms and approaches

  Organizers: Elmar Rueckert (Technische Universitaet Darmstadt), Martin
Riedmiller (Google DeepMind)


  Abstract:

  Modern robots are complex machines with many compliant actuators and
various types of sensors including depth and vision cameras, tactile
electrodes and dozens of proprioceptive sensors. The obvious challenges are
to process these high dimensional input patterns, memorize low dimensional
representations of them and to generate the desired motor commands to
interact in dynamically changing environments. Similar challenges exist in
brain machine interfaces (BMIs) where complex prostheses with perceptional
feedback are controlled, or in motor neuroscience where in addition
cognitive features need to be considered. Despite this broad research
overlap the developments happened mainly in parallel and were not ported or
exploited in the related domains. The main bottleneck for collaborative
studies has been a lack of interaction between the core robotics, the
machine learning and the neuroscience communities.

  Why is it now just the right time for interactions?

  - Latest developments based on deep neural networks have advanced the
capabilities of
    robotic systems by learning control policies directly from the high
dimensional
    sensor readings.
  - Many variants of networks have been recently developed including the
integration of feedback through
    recurrent connections, the projection to different feature spaces, may
be trained at
    different time scales and can be modulated through additional inputs.
  - These variants can be the basis for new models and concepts in motor
neuroscience,
    where simple feed forward structures were not sufficiently powerful.
  - Robotic applications demonstrated the feasibility of such networks for
real time
    control of complex systems, which can be exploited in BMIs.
  - Modern robots and new sensor technologies require models that can
integrate a huge
    amount of inputs of different dimension, at different rates and with
different noise
    levels. The neuroscience communities face such challenges and develop
sophisticated
    models that can be evaluated in robotic applications used as
benchmarks.
  - New learning rules can be tested on real systems in challenging
environments.

  Topics:
  - Convolutional Networks and Real-time Robotic and Prosthetic applications
  - Deep Learning for Robotics and Prosthetics
  - End-to-End Robotics / Learning
  - Feature Representations for Big Data
  - Movement Representations, Movement Primitives and Muscle Synergies
  - Neural Network Hardware Implementation, Neuromorphic Hardware
  - Recurrent Networks and Reservoirs for Control of high dimensional
systems
  - Reinforcement Learning and Bayesian Optimization in Neural Networks
from multiple reward sources
  - Sampling Methods and Spiking Networks for Robotics
  - Theoretical Learning Concepts, Synaptic Plasticity Rules for Neural
Networks

  Format:

  The goal of this workshop is to bring together researcher from the
robotics, the machine learning and the neuroscience communities. Robotic
applications can be a source and inspiration for theoretical concepts while
the sophisticated networks can provide the basis for new ideas and models
in neuroscience. In this context, among the questions which we intend to
tackle are

  Reinforcement Learning, Imitation, and Active Learning:
  - Which adaptations to reinforcement learning algorithms are necessary to
learn from few
    samples like animals?
  - How to learn from structured rewards?
  - How to learn abstract concepts of complex behavior that can be used in
transfer learning?
  - Which reinforcement learning methods can learn on multiple/different
time-scales?

  Model Representations and Features:
  - How to adapt to redundant input features?
  - What are proper models of state dependent signal noise?
  - How to represent multi dimensional and complex solution spaces?
  - How to represent and learn causal dependencies between features in
different spaces?

  Feedback and Control:
  - How can models of state dependent signal noise be used for control?
  - Which model features are sufficient to react to dynamically changing
distributions of
    the inputs or the motor commands?
  - Which movement policies and models are needed to control underacted
systems?
  - How to adapt to failures in control and in learning?

  Participants:
  This workshop will bring together researchers from the robotics, the
machine learning and the computational neuroscience communities. The goal
is to explore new ideas and concepts to   solve the complex control tasks
in robotics or prosthetics and to model the complex information
processing problems in neuroscience. Participants of the workshop
(inclusive of the audience) are encouraged to actively participate by
responding with questions and comments about the talks and give stand-up
talks. Please contact the organizers if you would like to reserve a priori
some time for expressing your view on a particular topic.



  ***************************************************************

-- 
Elmar Rueckert
Technische Universitaet Darmstadt, Germany
Tel. +49 6151-16-20074
Fax. +49-6151-1625375


More information about the robotics-worldwide mailing list