DeepMind Research Scientists Presentation Series at Politehnica University of Timisoara

  Date and Time
Thursday, October 4, 2018 - 16:00 to 17:30
UPT Library - UPT Conference Center, 2B, Vasile Parvan Bvd.

Politehnica University of Timişoara, through its Department of Computer and Information Technology, hosts the presentation series of Dr. Viorica Patraucean and Dr. Razvan Pascanu, research scientists at DeepMind London, part of the Google / Alphabet group.

The presentations will be held according to the following program:

16:00 - 16:30 Progress & Compress - a framework for continual learning
by Razvan Pascanu, research scientist at DeepMind London
Razvan Pascanu

Abstract: The first part of the talk represents a discussion on the continual learning problem for neural networks and its importance for the field. Then it concentrates on Progress & Compress (, a recent framework for continual learning published at ICML 2018, and discuss some of the open issues on this topic.

Short Bio: Razvan obtained his Ph.D. at Universite de Montreal, working with Yoshua Bengio on optimization, recurrent models and deep learning in general. His interests range from topics like optimization, neural networks to deep reinforcement learning, continual learning and structured neural networks models.

16:30 - 17:00 Massively parallel video networks
by Viorica Patraucean, research scientist at DeepMind London

Abstract: The presentation covers our recent work on designing efficient video networks ( ECCV2018) where we propose a new framework for deep video processing that leverages operation pipelining and multi-rate clocks within deep neural networks.

Short Bio: Viorica obtained her PhD from University of Toulouse in statistical image processing. She was a postdoc with Ecole Polytechnique Paris and University of Cambridge working on 3D and video processing, prior to joining DeepMind. She works mainly on Computer Vision problems.

17:00 - 17:30 TMLSS2018 and what's next
by Viorica Patraucean and Razvan Pascanu

15 min. presentation of the first edition of the TMLSS - Transylvanian Machine Learning Summer School and Q&A session.