Addressing Big Science challenges with Machine Learning

Slide 1

Slide 1 text

Addressing Big Science challenges with Machine Learning (ML) 1 7 Feb 2018, openatalks.ai Andrey Ustyuzhanin NRU HSE YSDA ICL

Slide 2

Slide 2 text

Andrey Ustyuzhanin 2 From D.Whiteson, J Cham book “We have no idea”

Slide 3

Slide 3 text

Andrey Ustyuzhanin 3

Slide 4

Slide 4 text

Dark Matter Andrey Ustyuzhanin 4 Illustrations from J. Cham; D. Whiteson. “We Have No Idea” https://en.wikipedia.org/wiki/Dark_matter

Slide 5

Slide 5 text

Gravitational Lenses Andrey Ustyuzhanin 5 http://www.spacetelescope.org/videos/heic0701j/

Slide 6

Slide 6 text

Lens modeling Andrey Ustyuzhanin 6 ▌ How Does The Background Source Truly Look Like? What Is The Undistorted Image? ▌ How Is Matter Distributed In The Lensing Structure?

Slide 7

Slide 7 text

Andrey Ustyuzhanin 7

Slide 8

Slide 8 text

Andrey Ustyuzhanin 8

Slide 9

Slide 9 text

Low-hanging fruits for ML Andrey Ustyuzhanin 9 ▌ Classify: lenses vs non-lenses ▌ Non-gradient optimization for parameters search or ▌ Train CNNs to predict (regression) parameters of the background object and mass distribution: Fast automated analysis of strong gravitational lenses with CNNs Hezaveh, Perreault Levasseur, Marshall, Nature Aug. 2017 : “10 million times faster than regular lens modeling: 0.01 seconds on GPU”

Slide 10

Slide 10 text

Quick self-intro Andrey Ustyuzhanin 10 ▌ Head of Laboratory of Methods for Big Data Analysis › Applying ML to natural sciences probmels › http://cs.hse.ru/lambda ▌ Yandex School of Data Analysis › Course on solving High Energy Physics problems with ML approaches ▌ Collaboration with experiments at CERN: › Particle physics: LHCb , SHiP (CERN) › Dark matter search: NEWSdm (Gran Sasso) › Cosmic ray (CRAYFIS)

Slide 11

Slide 11 text

New Physics (Dark Matter) search at CERN Andrey Ustyuzhanin 11 ▌ Standard Model is cool but is not the final answer: › Neutrino has mas › Why antimatter is so rare? › What is dark matter? ▌ Laboratory search for deviations: › SHiP

Slide 12

Slide 12 text

Search for Hidden Particles Andrey Ustyuzhanin 12 ▌ Physics cases: › Variety of Hidden Sector portals explored › Tau neutrino physics › Light Dark Matter (LDM) Search ▌ ML cases: › Experiment design (shield, emulsion optimization) › Signal/background separation in emulsion › Fast simulation

Slide 13

Slide 13 text

Muon Shield Design Bayesian optimization: “designed” magnets, that are 25% lighter Andrey Ustyuzhanin 13 http://iopscience.iop.org/article/10.1088/1742- 6596/934/1/012050/meta

Slide 14

Slide 14 text

Nuclear Emulsion Andrey Ustyuzhanin 14 ▌ After the passage of charged particles through the emulsion, a latent image is produced ▌ The emulsion chemical development makes Ag grains visible with an optical microscope Compton electron

Slide 15

Slide 15 text

Emulsion, electromagnetic showers Development of new software tools based on ML techniques for electron identification and energy measurement in photo emulsions Andrey Ustyuzhanin 15

Slide 16

Slide 16 text

Fast physics simulation Andrey Ustyuzhanin 16 https://github.com/hep-lbdl Arxiv: 1705.02355, 1701.05927

Slide 17

Slide 17 text

Cosmic rays (OMG particles) Andrey Ustyuzhanin 17

Slide 18

Slide 18 text

Cosmic Ray + Smart Phone = CRAYFIS Andrey Ustyuzhanin 18

Slide 19

Slide 19 text

Generating realistic CMOS-camera images Andrey Ustyuzhanin 19

Slide 20

Slide 20 text

ML challenges Andrey Ustyuzhanin 20 1. Realistic signal simulation 2. Fast data processing on smart phones 3. Tuning of simulator parameters 4. Fraud detection

Slide 21

Slide 21 text

Galaxy Zoo: science + human IQ Andrey Ustyuzhanin 21 https://arxiv.org/abs/0907.4155 http://bit.ly/2o4d2P8 ▌ Regular challenge: › Identify galaxies ▌ ’Occasional’ discoveries: › Green peas and voorwerps

Slide 22

Slide 22 text

Conclusion Andrey Ustyuzhanin 22 ▌ There is quite a bit of cool stuff going on in fundamental science › Dark matter, gravitational lenses, “OMG “cosmic rays, dwarf galaxies, … ▌ There are serious challenges for ML in Natural Sciences Domain › Experiment design, simulation tuning, anomaly/fraud detection, … ▌ AI challenge: › Find something no human has considered possible (green pea, voorwerps, etc) ▌ Summer school on Machine Learning for High Energy Physics, Oxford: › http://bit.ly/mlhep2018 http://cs.hse.ru/lambda anaderiRu@twitter

Slide 23

Slide 23 text

Backup Andrey Ustyuzhanin 23

Slide 24

Slide 24 text

Andrey Ustyuzhanin 24

Slide 25

Slide 25 text

References - Machine Learning for High Energy Physics, https://bit.ly/mlhep2018 - M. Nielson, Reinventing the discovery - C. Cardamone et al, Galaxy Zoo Green Peas: Discovery of A Class of Compact Extremely Star-Forming Galaxies https://arxiv.org/abs/0907.4155 - Google exa planet search: https://www.theverge.com/2017/12/14/16777394/google-nasa-ai- machine-learning-planets-astronomy

Slide 26

Slide 26 text

Andrey Ustyuzhanin 26

Slide 27

Slide 27 text

Andrey Ustyuzhanin 27 https://www.youtube.com/watch?v=Y9yQOb94yl0 https://www.youtube.com/watch?v=2qeT4DkEX-w