AI at CERN and SKA

Session

Day 1

17 Sept 2018, 10:00

Description

In this session we will focus on hardware and software infrastructure supporting ML

2. opening words

Dr Braam Peter

17/09/2018, 10:00

3. Partnering with industry for machine learning at HL-LHC

Dr Maria Girone (CTO CERN OpenLab)

17/09/2018, 10:05

The High Luminosity LHC (HL-LHC) represents an unprecedented computing challenge. For the program to succeed the current estimates from the LHC experiments for the amount of processing and storage required are roughly 50 times more than are currently deployed. Although some of the increased capacity will be provided by technology improvements over time, the computing budget is expected to be...

4. Emerging Use of DNNs

Mr Stephen Pawlowski (VP of Advanced Computing Solutions, Micron)

17/09/2018, 10:35

Abstract: Data is being created at an alarming rate and we need faster and more efficient machines and algorithms to make sense of this data. Though we will still need the performance of traditional high performance computing, there are characteristics and relationships in the data that are needing more non-traditional computing approaches for greater efficiency. This need is also coupled with...

5. Learning Deep Generative Models of Graphs

Dr Yujia Li (DeepMind)

17/09/2018, 11:05

Abstract: Graphs are fundamental data structures which concisely capture the relational structure in many important real-world domains, such as knowledge graphs, physical and social interactions, language, and chemistry. Here we introduce a powerful new approach for learning generative models over graphs, which can capture both their structure and attributes. Our approach uses graph neural...

6. Infrastructure for ML panel

17/09/2018, 11:50

Moderator: Dr Peter Braam
Panelists: Dr Maria Girone, Dr Yujia Li, Dr Bojan Nikolic, Stephen Pawlowski

7. Deep Learning for Science: Opening the Pandora Box

Dr Shirley Ho

17/09/2018, 14:00

Dr. Shirley Ho, Group Leader, Flatiron Institute, Cosmology X Data Science, CCA

Abstract: Scientists have always attempted to identify and document analytic laws that underlie physical phenomena in nature. The process of finding natural laws has always been a challenge that requires not only experimental data, but also theoretical intuition. Often times, these fundamental physical laws are...

8. Two computing challenges for particle physics : the tracking challenge and event simulation with Generative Adversarial Networks

Dr David Rousseau

17/09/2018, 14:30

Dr. David Rousseau, HEP Physicist (ATLAS software and Higgs Physics) at LAL, Orsay, France

Abstract: I will expand on two specific lines of effort to solve the computational challenge at the LHC. (i) LHC experiments need to reconstruct the trajectory of particles from the few precise measurements in the detector. One major process is to « connect the dots », that is associate together the...

9. Too much of a good thing : how to drink new physics from a 40 Tb/s firehose

Dr Vladimir "Vava" Gligorov

17/09/2018, 15:15

Dr. Vladimir “Vava” Gligorov, Research Scientist at CNRS/LPNHE

Abstract: LHCb is one of the four major experiments at the Large Hadron Collider (LHC) at CERN. It searches for particles and forces beyond our current physics theories, in particular
by making highly precise measurements of the properties of the particles produced in the LHC collisions. Doing so requires analyzing an enormous...

10. Deep Learning for the future of the Large Hadron Collider

Dr Maurizio Pierini

17/09/2018, 15:45

Dr. Maurizio Pierini, CERN Physicist working on the CMS experiment at the Large Hadron Collider

Abstract: The High-Luminosity LHC phase, scheduled for 2025, will challenge the commonly accepted solutions for tasks such as event reconstruction, real-time processing, large dataset simulation, etc. Deep Learning is considered as a strong candidate to solve this issue, by speeding up the task...

11. Panel: ML Specific to HEP

17/09/2018, 16:45

Moderator: Dr Alan Barr
Panelists: Dr. David Rousseau, Dr. Vladimir "Vava" Gligorov, Dr. Maurizio Pierini, Dr. Jennifer Thompson