Lisa_seminaires Juillet 2018

lisa_seminaires@iro.umontreal.ca

3 participants
5 discussions

[Tea Talk] Petar Veličković (Cambridge / Mila) August 32018 10:30 AA3195
by Michael Noukhovitch 03 Aoû '18

03 Aoû '18

This week we have *Petar Veličković * from * Cambridge/Mila * giving a talk on *August 3rd 2018* at *10:30* in room *AA3195* Will this talk be streamed <https://mila.bluejeans.com/1365483656/webrtc>? yes Come to the talk and make sure to pay attention, because this talk should be great to connect the dots! Michael *TITLE* Keeping our graphs attentive *KEYWORDS *graph structured, attention, computational biology *ABSTRACT* A multitude of important real-world datasets (especially in biology) come together with some form of graph structure: social networks, citation networks, protein-protein interactions, brain connectome data, etc. Extending neural networks to be able to properly deal with this kind of data is therefore a very important direction for machine learning research, but one that has received comparatively rather low levels of attention until very recently. Attentional mechanisms represent a very promising direction for extending the established convolutional operator on images to work on arbitrary graphs, as they satisfy many of the desirable features for a convolutional operator. Through this talk, I will focus on my work on Graph Attention Networks (GATs), where these theoretical properties have been further validated by solid results on transductive as well as inductive node classification benchmarks. I will also outline some of the earlier efforts towards deploying attention-style operators on graph structures, as well as very exciting recent work that expands on GATs and deploys them in more general circumstances (such as EAGCN, DeepInf, and applications to solving the Travelling Salesman Problem). Time permitting, I will also present some of the relevant related graph-based work in the computational biology and medical imaging domains that I have been involved in. *BIO* Petar Veličković is currently a final-year PhD student in Machine Learning and Bioinformatics at the Department of Computer Science and Technology of the University of Cambridge. He also holds a BA degree in Computer Science from Cambridge, having completed the Computer Science Tripos in 2015. In addition, he has been involved in research placements at Nokia Bell Labs (working with Nicholas Lane) and the Montréal Institute of Learning Algorithms (working with Adriana Romero and Yoshua Bengio). His current research interests broadly involve devising neural network architectures that operate on nontrivially structured data (such as graphs), and their applications in bioinformatics and medicine. He has published his work in these areas at both machine learning venues (ICLR, NIPS ML4H, ICML WCB) and biomedical venues and journals (Bioinformatics, PervasiveHealth)

2 3

No [Tea Talk] This Week
by Michael Noukhovitch 24 Jul '18

24 Jul '18

EOM

1 0

[Tea Talk] Glen Berseth (UBC) July 20 2018 10:30 AA3195
by Michael Noukhovitch 20 Jul '18

20 Jul '18

This week we have *Glen Berseth * from * UBC*, who will be interning with Chris Pal, giving a talk on *July 20 2018* at *10:30* in room *AA3195* Will this talk be streamed <https://mila.bluejeans.com/1365483656/webrtc>? Yes! Want to meet with Glen? Glen is only available until 2pm on Friday, so send him an email directly (gberseth(a)cs.ubc.ca) and perhaps invite him to lunch :) Given how many tea talks we've had, it should be a breeze to find your way by moving your legs and walking to come to this tea talk! Michael *P.S.* We still don't have a speaker for next week's talk, so if you're interested in giving a talk please slack or email me! *TITLE* Scalable Deep Reinforcement Learning for Physics-Based Motion Control *KEYWORDS *hierarchical RL, meta-learning, multi-task learning *ABSTRACT* Motion control in physics-based animation is challenging due to complex dynamics and discontinuous contacts. Many previous control methods that produce walking motions are very stiff, only work in particular environments and require significant manual tuning to get functioning. In this work, we progress the state-of-the-art in physics-based character animation in a number of directions using machine learning methods. We present three contributions that build upon the current research on motion control using deepRL. First, we show that decomposing tasks into a hierarchy increase learning efficiency by operating across multiple time scales on a complex locomotion and navigation task. Second, we investigate improved action exploration methods to sample more promising actions on robots and in simulation using forward dynamics distributions. This sampling strategy has been shown to improve sample efficiency for a number of problems, including many from the OpenAI Gym. Last, we consider a new algorithm to progressively learn and integrate new skills producing a robust and multi-skilled physics-based controller. This algorithm combines the skills of experts together and then applies transfer learning methods to initialize and accelerate the learning of new skills. *BIO* Glen Berseth is a PhD candidate at the Department of Computer Science at the University of British Columbia where he works on reinforcement learning, machine learning and motion planning. He received the BSc degree in Computer Science from York University in 2012 and his MSc from York University under the supervision of Petros Faloutsos in 2014 for optimization and authoring crowd simulations. He has published in a wide range of areas including computer animation, machine learning and robotics and is an NSERC scholarship award holder.

2 1

No [Tea Talk] on July 13 2018
by Michael Noukhovitch 11 Jul '18

11 Jul '18

*No talk on* *July 13 2018* Have fun at ICML! Michael

1 0

[Tea Talk] ICML Lightning Talks (Mila) July 6 2018 10:30AM AA1177
by Michael Noukhovitch 06 Jul '18

06 Jul '18

This week we have the second edition of the lightning talk tradition, ICML-edition, it will be on *Friday July 6 2018* at *10:30AM* in room *AA1177.* *Note the different room, AA1177* Will this talk be streamed <https://mila.bluejeans.com/809027115/webrtc>? Yes, but certain speakers may not be streamed I found $10 on the ground today so I will be buying $10 worth of snacks for the talk to sweeten the deal. Don't miss this chance to see lightning strike twice! Michael *WHAT IT IS* Mila authors of ICML-accepted conference and workshop papers do quick, 5 minute presentations of their work *PAPERS SIGNED UP SO FAR (please sign up!)* Focused Hierarchical RNNs for Conditional Sequence Processing Nan Ke · Konrad Zolna · Alessandro Sordoni · Zhouhan Lin · Adam Trischler · Yoshua Bengio · Joelle Pineau · Laurent Charlin · Christopher Pal Neural Autoregressive Flows Chin-Wei Huang · David Krueger · Alexandre Lacoste · Aaron Courville Approximate Exploration through State Abstraction Adrien Ali Taiga, Aaron Courville, Marc Bellemare Negative Momentum for Improved Game Dynamics Gauthier Gidel Reyhane Askari Mohammad Pezeshki Gabriel Huang Rémi Lepriol Ioannis Mitliagkas Simon Lacoste-Julien Oríon : Experiment Version Control for Efficient Hyperparameter Optimization Christos Tsirigotis, Xavier Bouthillier, François Corneau-Tremblay, Peter Henderson, Reyhane Askari, Samuel Lavoie-Marchildon, Tristan Deleu, Dendi Suhubdy, Michael Noukhovitch, Frédéric Bastien, Pascal Lamblin Attentive cross-modal paratope prediction Andreea Deac, Petar Veličković, Pietro Sormanni

2 3

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

Lisa_seminaires Juillet 2018