1st Terascale School of Machine Learning
from
Monday, 22 October 2018 (08:00)
to
Friday, 26 October 2018 (14:00)
Monday, 22 October 2018
09:30
Introduction to Python (optional pre-tutorial)
Introduction to Python (optional pre-tutorial)
09:30 - 11:00
Room: SR4
11:00
Coffee break
Coffee break
11:00 - 11:20
Room: SR4
11:20
Introduction to numPy (optional pre-tutorial)
Introduction to numPy (optional pre-tutorial)
11:20 - 13:00
Room: SR4
13:00
Registration
Registration
13:00 - 14:00
Room: SR4
14:00
Welcome
-
Isabell-A. Melzer-Pellmann
(
DESY
)
Welcome
Isabell-A. Melzer-Pellmann
(
DESY
)
14:00 - 14:10
Room: SR4
14:10
Introduction to Machine Learning (part I)
-
Fedor Ratnikov
Introduction to Machine Learning (part I)
Fedor Ratnikov
14:10 - 15:40
Room: SR4
15:40
Coffee break
Coffee break
15:40 - 16:00
Room: SR4
16:00
Introduction to Machine Learning (part II)
Introduction to Machine Learning (part II)
16:00 - 17:30
Room: SR4
17:30
TMVA Tutorial
-
Lorenzo Moneta
TMVA Tutorial
Lorenzo Moneta
17:30 - 19:00
Room: SR4
Tuesday, 23 October 2018
09:30
Introduction to Deep Learning (part I)
-
Dirk Kruecker
(
DESY
)
Introduction to Deep Learning (part I)
Dirk Kruecker
(
DESY
)
09:30 - 11:00
Room: SR4
11:00
Coffee break
Coffee break
11:00 - 11:20
Room: SR4
11:20
Introduction to deep learning + pyTorch tutorial (part II)
-
Dirk Kruecker
(
DESY
)
Introduction to deep learning + pyTorch tutorial (part II)
Dirk Kruecker
(
DESY
)
11:20 - 13:00
Room: SR4
13:00
Lunch break
Lunch break
13:00 - 14:00
Room: SR4
14:00
Introduction to Deep Learning + pyTorch tutorial (part III)
-
Dirk Kruecker
(
DESY
)
Introduction to Deep Learning + pyTorch tutorial (part III)
Dirk Kruecker
(
DESY
)
14:00 - 15:30
Room: SR4
15:30
Coffee break
Coffee break
15:30 - 15:50
Room: SR4
15:50
Introduction to Deep Learning + pyTorch tutorial (part IV)
-
Dirk Kruecker
(
DESY
)
Introduction to Deep Learning + pyTorch tutorial (part IV)
Dirk Kruecker
(
DESY
)
15:50 - 17:30
Room: SR4
Wednesday, 24 October 2018
09:30
Deep Learning - Convolutional and recurrent networks
-
Gregor Kasieczka
(
Institut fuer Experimentalphysik / UHH
)
Deep Learning - Convolutional and recurrent networks
Gregor Kasieczka
(
Institut fuer Experimentalphysik / UHH
)
09:30 - 11:00
Room: SR4
11:00
Coffee break
Coffee break
11:00 - 11:20
Room: SR4
11:20
Adversarial Frameworks - from traditional GANs to WGANs and progressive GANs
-
Jonas Glombitza
(
RWTH Aachen
)
Adversarial Frameworks - from traditional GANs to WGANs and progressive GANs
Jonas Glombitza
(
RWTH Aachen
)
11:20 - 12:50
Room: SR4
12:50
Lunch break
Lunch break
12:50 - 14:00
Room: SR4
14:00
Tutorial: Tensorflow
-
Adam Elwood
(
DESY
)
Tutorial: Tensorflow
Adam Elwood
(
DESY
)
14:00 - 15:30
Room: SR4
15:30
Coffee break
Coffee break
15:30 - 15:50
Room: SR4
15:50
Tutorial: Keras
-
Christian Contreras Campana
(
DESY
)
Tutorial: Keras
Christian Contreras Campana
(
DESY
)
15:50 - 17:50
Room: SR4
17:50
Break
Break
17:50 - 18:00
Room: SR4
18:00
Networked data-science for research, academic communities and beyond
-
Andrey Ustyuzhanin
Networked data-science for research, academic communities and beyond
Andrey Ustyuzhanin
18:00 - 19:00
Room: SR4
There is an exceptional way of doing data-driven research employing networked community. The following examples can illustrate the approach: Galaxy Zoo or Tim Gower’s blog. However many cases of collaboration with the data-science community within competitions organised on Kaggle or Coda Lab platforms usually get limited by restrictions on those platforms. Common Machine Learning quality metrics do not necessarily correspond to the original research goal. Constraints imposed by the problem statement typically look artificial for ML-community. Preparing a perfect competition takes a considerable amount of efforts. On the contrary research process requires a lot of flexibility and ability to look at the problem from different angles. I’ll describe the alternative research collaboration process can bridge the gap between domain-specific research and data science community. Notably, it can involve academic researchers, younger practitioners and all enthusiasts who are willing to contribute. Such research process can be supported by an open computational platform that will be described along with essential examples for the audience of the workshop.
19:00
School dinner
School dinner
19:00 - 22:00
Room: SR4
Thursday, 25 October 2018
09:30
Machine learning outside HEP
-
Simone Frintrop
Machine learning outside HEP
Simone Frintrop
09:30 - 10:30
Room: SR4
10:30
Coffee break
Coffee break
10:30 - 10:50
Room: SR4
10:50
Machine Learning with Less or no Simulation Dependence
-
Benjamin Nachman
Machine Learning with Less or no Simulation Dependence
Benjamin Nachman
10:50 - 12:30
Room: SR4
12:30
Lunch break
Lunch break
12:30 - 14:00
Room: SR4
14:00
Challenge
-
Gregor Kasieczka
(
Institut fuer Experimentalphysik / UHH
)
Lydia Brenner
(
DESY
)
Challenge
Gregor Kasieczka
(
Institut fuer Experimentalphysik / UHH
)
Lydia Brenner
(
DESY
)
14:00 - 15:30
Room: SR4
15:30
Coffee break
Coffee break
15:30 - 15:50
Room: SR4
15:50
Challenge (continued)
Challenge (continued)
15:50 - 18:00
Room: SR4
Friday, 26 October 2018
09:30
Advanced Deep Learning: Understanding the black box, physics, ...
-
Gregor Kasieczka
(
Institut fuer Experimentalphysik / UHH
)
Advanced Deep Learning: Understanding the black box, physics, ...
Gregor Kasieczka
(
Institut fuer Experimentalphysik / UHH
)
09:30 - 10:30
Room: SR4
10:30
Coffee break
Coffee break
10:30 - 10:50
Room: SR4
10:50
Presentation of the best three challenge results
Presentation of the best three challenge results
10:50 - 11:20
Room: SR4
11:20
Likelihood-free inference, its connections with a typical analysis and recent developments in ML
-
Gilles Louppe
Likelihood-free inference, its connections with a typical analysis and recent developments in ML
Gilles Louppe
11:20 - 12:50
Room: SR4
12:50
Goodbye
Goodbye
12:50 - 13:00
Room: SR4