Deep Learning in the Natural Sciences

Session

Talk

28 Feb 2019, 13:00

Hamburg

Conveners

Talk: Talks I

• Marcus Brueggen

Talk: Talks II

• There are no conveners in this block

Talk: Talks III

• Johannes Haller (CERN)

Talk: Talks IV

• Gregor Kasieczka (Hamburg University (DE))

6. Opening

Gregor Kasieczka (Hamburg University (DE)), Marcus Brueggen

28/02/2019, 13:00

5. Collision Course: Particle Physics as a Machine-Learning Testbed

Jesse Thaler (MIT)

28/02/2019, 13:20

7. Machine Learning Techniques in Cosmological Simulation

Claudio Gheller

28/02/2019, 14:00

8. Low-dose X-ray Imaging with Deep Neural Networks

Xiaogang Yang

28/02/2019, 14:40

9. Machine Learning Techniques in Astroparticle Physics

Dominik Elsaesser

28/02/2019, 15:40

10. Rise of the Tagging Machines

Tilman Plehn (Heidelberg University), Tilman Plehn

28/02/2019, 16:20

11. Machine Learning for Diffractive Imaging and Crystallography

Filipe Maia

28/02/2019, 17:00

12. Deep Learning in Particle and Astroparticle Physics

Martin Erdmann (Rheinisch Westfaelische Tech. Hoch. (DE))

01/03/2019, 09:00

4. A metric for collider events

Patrick Komiske (Massachusetts Institute of Technology)

01/03/2019, 09:40

When are two collider events similar? In this talk, I will answer this question by developing a metric between the radiation patterns of events. The metric is based on the well known earth mover’s distance, and intuitively is the minimum “work” required to rearrange the energy flow of one event into the other. With a metric in hand, I will discuss and demonstrate numerous tools for analyzing...

14. Radio Galaxy Classifications with Deep Learning

Vesna Lukic

01/03/2019, 10:00

2. Particle identification on the DAMPE experiment

David Francois Droz (Universite de Geneve (CH))

01/03/2019, 10:20

The Dark Matter Particle Explorer (DAMPE) is a space-borne particle detector and cosmic rays observatory in operations since 2015, equipped with alongside other instruments a deep calorimeter able to detect electrons up to an energy of 10 TeV and cosmic rays up to 100 TeV. The large proton and ion background in orbit requires a powerful electron identification method. We explore a neural...

15. Machine learning with augmentation for boosting di-Higgs searches at the LHC

Won Sang Cho (Seoul National University)

01/03/2019, 10:40

16. Application of Generative Models to Natural Science

Fedor Ratnikov, Fedor Ratnikov (Yandex School of Data Analysis (RU))

01/03/2019, 11:30

3. Towards data-driven particle physics classifiers

Eric Metodiev (Massachusetts Institute of Technology)

01/03/2019, 12:10

Deep learning in particle physics often relies on imperfect simulations due to the lack of real labelled data, which risks learning mismodeling artifacts rather than the underlying physics. In this talk, I discuss the prospects for training classifiers directly on collider data using mixed samples, drawing from techniques in weak supervision and topic modeling. Using the example of quark...

13. Autoencoding New Physics

Jennifer Thompson (ITP Heidelberg), Jennifer Thompson (ITP Heidelberg)

01/03/2019, 12:30

17. CNN Classification of X-ray Selected Clusters

Matej Kosiba

01/03/2019, 12:50

18. Closing Discussion

Peter Schleper (Hamburg University (DE))

01/03/2019, 13:10

1. Exploring Hybrid Deep Learning Architecture for Experimental HEP Data Analysis

Mr Yavar Taheri Yeganeh (Shahid Beheshti University)

Deep learning has shown a promising future in physics’ data analysis and is anticipated to revolutionize LHC discoveries.
Designing an optimal algorithm may seem to be the most challenging task in machine learning progress especially in HEP due to the high dimensionality and extreme complexity of the data.
Physical knowledge can be employed in designing and modifying of the algorithm’s...