Kickoff Workshop

Dec. 10, 2020 from 14:45 to 19:00 CET online

WP5 has held its kickoff workshop on Dec. 10, 2020 from 14:45 to 19:00 CET with the following schedule:

14:45 - 15:00 - Gathering

15:00 - 16:00 - Invited talk by Murray Shanahan (Imperial College London, Deep Mind) - chaired by Hector Geffner - video

16:00 - 16:15 - Break

16:15 - 17:45 - Scientific panel lead by task leaders open to everyone (Giuseppe De Giacomo, Hector Geffner, Malte Helmert, Andreas Herzig, Gerhard Lakemeyer, and Paolo Traverso, focussing on key scientific challenges, benchmarks, and setting up collaborations) - chaired by Kristian Kersting - video

17:45 - 18:00 - Break

18:00 - 19:00 - Open discussion on how to organize WP activities (Workshops, micro-projects, site, discussion groups, phd/postdocs managed activities, etc)

Invited talk

SPEAKER: Murray Shanahan (Imperial College London, Deep Mind)

TITLE: Common Sense Physics in the Era of Deep Learning

ABSTRACT: The challenge of endowing computers with common sense remains one of the major obstacles to achieving the sort of general artificial intelligence envisioned by the field’s founders. A large part of human common sense pertains to the physics of the everyday world, and rests on a foundational understanding of such concepts as objects, motion, obstruction, containers, portals, support, and so on. In this talk I will discuss the challenge of common sense physics in the context of contemporary progress in deep reinforcement learning.

BIO: Murray Shanahan is Professor of Cognitive Robotics in the Dept. of Computing at Imperial College London, and a senior research scientist at DeepMind. Educated at Imperial College and Cambridge University (King’s College), he became a full professor at Imperial in 2006, and joined DeepMind in 2017. His publications span artificial intelligence, robotics, machine learning, logic, dynamical systems, computational neuroscience, and philosophy of mind. He has written several books, including “Embodiment and the Inner Life” (2010) and “The Technological Singularity” (2015). His main current research interests include deep reinforcement learning, representation learning, and common sense.

Transcriptions