Machine Learning scientific competitions and datasets

Rousseau, David; Ustyuzhanin, Andrey

Machine Learning scientific competitions and datasets

Dec 15, 2020

43 pages

e-Print:

2012.08520 [physics.data-an]

View in:

pdf

reference search3 citations

Citations per year

Abstract: (arXiv)

A number of scientific competitions have been organised in the last few years with the objective of discovering innovative techniques to perform typical High Energy Physics tasks, like event reconstruction, classification and new physics discovery. Four of these competitions are summarised in this chapter, from which guidelines on organising such events are derived. In addition, a choice of competition platforms and available datasets are described

Note:

To appear in Artificial Intelligence for High Energy Physics, World Scientific Publishing

CERN LHC Coll
new physics

References(49)

Figures(11)

[1]

Imagenet classification with deep convolutional neural networks, in Advances in Neural Information Processing Systems 25, F. Pereira, C. J. C. Burges, L. Bottou, and K. Q. Weinberger (eds.) / pp. 1097-1105. Curran Associates, Inc

A. Krizhevsky
,
I. Sutskever
,
G.E. Hinton

[2]

50 years of data science, in Tukey Centennial workshop

D. Donoho

[3]

Machine learning at the energy and intensity frontiers of particle physics

Alexander Radovic
(
- William-Mary Coll.
)
,
Mike Williams
(
- MIT
)
,
David Rousseau
(
- Orsay, LAL
)
,
Michael Kagan
(
- SLAC
)
,
Daniele Bonacorsi
(
- U. Bologna (main) and
- INFN, Bologna
)

et al.

- Nature 560 (2018) 7716, 41-48
•
DOI:
- 10.1038/s41586-018-0361-2

[4]

Searching for Exotic Particles in High-Energy Physics with Deep Learning

Pierre Baldi
(
- UC, Irvine
)
,
Peter Sadowski
(
- UC, Irvine
)
,
Daniel Whiteson
(
- UC, Irvine and
- Pennsylvania U.
)

- Nature Commun. 5 (2014) 4308
•
e-Print:
- 1402.4735
•
DOI:
- 10.1038/ncomms5308

[5]

Learning to discover: the Higgs boson machine learning challenge - documentation, CERN Open Data Portal.

C. Adam-Bourdarios
,
G. Cowan
,
C. Germain
,
I. Guyon
,
B. Kégl

et al.

•
DOI:
- 10.7483/OPENDATA.ATLAS.MQ5J.GHXA

[6]

Dataset from the ATLAS Higgs boson machine learning challenge 2014, CERN Open Data Portal.

ATLAS collaboration

Collaboration

•
DOI:
- 10.7483/OPENDATA.ATLAS.ZBP2.M5T8

[7]

The Higgs boson machine learning challenge, PMLR, Montreal, Canada, 13 Dec

C. Adam-Bourdarios
,
G. Cowan
,
C. Germain
,
I. Guyon
,
B. Kégl

et al.

[8]

Proceedings of Machine Learning Research, vol. 42 of Proceedings of Machine Learning Research. PMLR

G. Cowan
,
C. Germain
,
I. Guyon
,
B. Kégl
,
D. Rousseau

[9]

Evidence for the Higgs-boson Yukawa coupling to tau leptons with the ATLAS detector

ATLAS

Collaboration

•

Georges Aad
(
- Marseille, CPPM
)

et al.

- JHEP 04 (2015) 117
•
e-Print:
- 1501.04943
•
DOI:
- 10.1007/JHEP04(2015)117

[10]

Asymptotic formulae for likelihood-based tests of new physics

Glen Cowan
(
- Royal Holloway, U. of London
)
,
Kyle Cranmer
(
- New York U.
)
,
Eilam Gross
(
- Weizmann Inst.
)
,
Ofer Vitells
(
- Weizmann Inst.
)

- Eur.Phys.J.C 71 (2011) 1554,
- Eur.Phys.J.C 73 (2013) 2501 (erratum)
•
e-Print:
- 1007.1727
•
DOI:
- 10.1140/epjc/s10052-011-1554-0

[11]

XGBoost: A Scalable Tree Boosting System

e-Print:
- 1603.02754
•
DOI:
- 10.1145/2939672.2939785

[12]

F. Chollet

[13]

Evidence for the associated production of the Higgs boson and a top quark pair with the ATLAS detector

ATLAS

Collaboration

•

Morad Aaboud
(
- Oujda U.
)

et al.

- Phys.Rev.D 97 (2018) 7, 072003
•
e-Print:
- 1712.08891
•
DOI:
- 10.1103/PhysRevD.97.072003

[14]

Introduction to machine learning.

L. Polson
,
A. Scaife

[15]

Fouille de données et médias sociaux. tp1 : Higgs boson machine learning challenge. (in french).

O. Schwander

[16]

Lessons learned from the higgs boson kaggle challenge.

J. Wittenauer

[17]

Inference for Clustering and Anomaly Detection. PhD thesis, Carnegie Mellon University, Department of Statistics & Data Science

P. Chakravarti

[18]

On the impact of selected modern deep-learning techniques to the performance and celerity of classification models in an experimental high-energy physics use case

Giles Chatham Strong
(
- LIP, Lisbon
)

- Mach.Learn.Sci.Tech. 1 (2020) 045006
•
e-Print:
- 2002.01427
•
DOI:
- 10.1088/2632-2153/ab983a

[19]

victor-estrade/datawarehouse: First release.

V. Estrade

•
DOI:
- 10.5281/zenodo.1887847

[20]

Adversarial learning to eliminate systematic errors: a case study in High Energy Physics, Proceedings of the Deep Learning for Physical Sciences Workshop at NIPS .. https: //dl4physicalsciences.github.io/files/nips_dlps__1.pdf