Machine Learning for Jet Physics

Session

Experimental/Practical aspects of learning with jets (Chairs: Ben Hooberman and Daniel Elvira)

15 Nov 2018, 14:00

One West (WH1W) (Fermilab)

33. Introduction and overview (20'+10')

15/11/2018, 14:00

34. Machine Learning for Jet Calibration in ATLAS (20'+5')

Aviv Ruben Cukierman (SLAC National Accelerator Laboratory (US))

15/11/2018, 14:30

25. End-to-end jet identification for quark/gluon discrimination using CMS Open Data (20'+5')

Michael Andrews (Carnegie-Mellon University (US))

15/11/2018, 15:00

Jet identification is a very active area of applied machine learning research in particle physics, benefitting from a wide array of ideas and algorithms. Among these is the idea of building jet “images". However, many image-based implementations have struggled to compete with the current state-of-the-art classifiers that are dominated by specialized networks that rely on higher-level inputs....

16. Pulling Out All the Tops with Computer Vision and Deep Learning (20'+5')

Sebastian Macaluso

15/11/2018, 16:15

We apply computer vision with deep learning -- in the form of a convolutional neural network (CNN) -- to build a highly effective boosted top tagger. Previous work (the ``DeepTop" tagger of Kasieczka et al) has shown that a CNN-based top tagger can achieve comparable performance to state-of-the-art conventional top taggers based on high-level inputs. Here, we introduce a number of...

14. Fast inference of jet substructure classifiers with FPGAs (20'+5')

Zhenbin Wu (University of Illinois at Chicago (US))

15/11/2018, 16:40

Recent results at the Large Hadron Collider (LHC) have pointed to enhanced physics capabilities through the improvement of the real-time event processing techniques. Machine learning methods are ubiquitous and have proven to be very powerful in LHC physics, and particle physics as a whole. However, exploration of the use of such techniques in low-latency, low-power FPGA hardware has only just...

3. Modern jet machine-learning classification in real time (20'+5')

Konstantin Gizdov (The University of Edinburgh (GB))

15/11/2018, 17:05

We demonstrate the ability to create drone from a wide range of classifiers, with a particular emphasis on the application to modern jet classification. Machine learning is increasingly dominating the preferred tool for the classification of jets. However, as experiment data rates increase by orders of magnitude, such technologies become expensive in terms of time and performance. In light of...

40. Heavy flavour identification for boosted resonances and large cone jets in CMS (20'+5')

Javier Mauricio Duarte (Fermi National Accelerator Lab. (US))

15/11/2018, 17:30

Physics with boosted objects has been an increasingly interesting topic in the last years. Modern machine learning techniques, and Deep Learning in particular, have changed the landscape providing new taggers with significant performance boost. The presentation will focus on the taggers for the boosted regime, DeepAK8, DeepDoubleB, and DeepDoubleC and the strategies to measure their...