Conveners
Parallel Session: Computing & Machine Learning
- Taritree Wongjirad (MIT)
- Sergei Gleyzer (University of Florida)
- Oliver Gutsche (Fermi National Accelerator Laboratory)
Parallel Session: Computing & Machine Learning
- Oliver Gutsche (Fermi National Accelerator Laboratory)
- Sergei Gleyzer (University of Florida)
- Taritree Wongjirad (MIT)
Parallel Session: Computing & Machine Learning
- Sergei Gleyzer (University of Florida)
- Oliver Gutsche (Fermi National Accelerator Laboratory)
- Taritree Wongjirad (MIT)
Ms
Lucy Linder
(Lawrence Berkeley National Lab)
12/9/18, 4:00 PM
Computing
Oral Presentation
D-Wave Systems Quantum Annealer (QA) finds the ground state of a Hamiltonian expressed as:
$O(a;b;q)=\sum_{i=1}^N{a_i q_i} +\sum_{i}^N\sum_{j < i}^N{b_{ij} q_i q_j}$
This Quantum Machine Instruction (QMI) is equivalent to a Quadratic Unconstrained Binary Optimization (QUBO) and can be transformed easily into an Ising model or a Hopfield network.
Following Stimpfl-Abele [“Fast track...
Andrey Elagin
(University of Chicago)
12/9/18, 4:30 PM
Computing
Oral Presentation
I will discuss application of machine learning techniques for identification of a two-track
single-vertex event topology of double-beta decay events in a liquid scintillator detector. Event topologies of background events differ in number of tracks and/or in number of verticies and, in some cases, by relative timing of secondary particles. These topological differences between signal and...
Dr
Emanuele Usai
(Brown University)
12/9/18, 5:00 PM
Computing
Oral Presentation
From heavy flavour jet identification to the discovery of the Higgs boson, machine learning algorithms have become an increasingly important tool for physics analysis and event reconstruction at the Large Hadron Collider (LHC). We present an innovative approach to particle and event reconstruction at the LHC, called end-to-end deep learning, that combines modern deep learning algorithms with...
Dr
Kazuhiro Terao
(SLAC National Accelerator Laboratory)
12/9/18, 5:30 PM
Computing
Oral Presentation
Liquid Argon Time Projection Chambers (LArTPCs) are capable of recording images of charged particle tracks with breathtaking resolution. Such detailed information will allow LArTPCs to perform accurate particle identification and calorimetry, making it the detector of choice for many current and future neutrino experiments. However, analyzing such images can be challenging, requiring the...
Vyacheslav Krutelyov
12/10/18, 1:30 PM
Computing
Oral Presentation
Leading planned or considered hadron colliders are expected to produce data in collisions with average number of simultaneous interactions per beam bunch crossing of several hundred. These include both the high luminosity LHC upgrade currently in preparation and the possible high energy LHC upgrade as well as a future circular collider FCC-hh. Execution of charged particle track reconstruction...
Dr
Markus Diefenthaler
(Jefferson Lab)
12/10/18, 2:00 PM
Computing
Oral Presentation
Experiments in Nuclear Physics (NP) have unique requirements on their data acquisition and computing due to the multiple channel and multi-dimensional challenges in their measurements. While there have been remarkable advances in microelectronics capabilities, computing, and data science over the last decade, the research model of NP has not changed for many decades. With the start of the 12...
Jia Low
(University of Florida)
12/10/18, 2:30 PM
Computing
Oral Presentation
In order to preserve its ability to do physics at the electroweak scale in the HL-LHC era, CMS experiment has to maintain low trigger thresholds that are robust against high intensity and large number of interactions per bunch crossing expected at the HL-LHC. Specifically, the muon trigger transverse momentum (pT) thresholds currently used cannot be maintained at the HL-LHC without improving...
Dylan Rankin
(MIT)
12/10/18, 3:00 PM
Computing
Oral Presentation
Machine learning is becoming ubiquitous across HEP. There is great potential to improve trigger and DAQ performances with it. However, the exploration of such techniques within the field in low latency/power FPGAs has just begun. We present HLS4ML, a user-friendly software, based on High-Level Synthesis (HLS), designed to deploy network architectures on FPGAs. As a case study, we use HLS4ML...
Laura Domine
12/11/18, 8:00 AM
Computing
Oral Presentation
From a breakthrough revolution, Deep Learning (DL) has grown to become a de-facto standard technique in the fields of artificial intelligence and computer vision. In particular Convolutional Neural Networks (CNNs) are shown to be a powerful DL technique to extract physics features from images: They were successfully applied to the data reconstruction and analysis of Liquid Argon Time...
Prof.
Sudhir Malik
(University of Puerto Rico Mayaguez)
12/11/18, 8:30 AM
Computing
Oral Presentation
The HEP community faces a deluge of data in the coming decade from existing, upgraded and major new facilities. The Large Hadron Collider (LHC) at the European Laboratory for Particle Physics (CERN) will continue to generate ever increasing amounts of data, with a major upgrade in 2026. In the U.S., the Long-Baseline Neutrino Facility (LBNF) and Deep Underground Neutrino Experiment (DUNE) will...