ONLINE: Workshop on Perspectives and Applications of Deep Learning for Accelerated Scientific Discovery in Physics
from
Thursday 14 May 2020 (09:00)
to
Friday 15 May 2020 (16:00)
Monday 11 May 2020
Tuesday 12 May 2020
Wednesday 13 May 2020
Thursday 14 May 2020
09:00
Welcome
-
Heloisa Bordallo
(
NBI
)
Welcome
Heloisa Bordallo
(
NBI
)
09:00 - 09:15
09:15
Machine learning and particle physics
-
Andreas Salzburger
(
CERN
)
Machine learning and particle physics
Andreas Salzburger
(
CERN
)
09:15 - 10:00
10:00
Data Challenges for accelerating scientific discovery at Neutron facilities
-
Jonathan Taylor
(
ess
)
Data Challenges for accelerating scientific discovery at Neutron facilities
Jonathan Taylor
(
ess
)
10:00 - 10:45
10:45
coffe break
coffe break
10:45 - 11:15
11:15
Collaboration on analysis of 3D image data the QIM Center
-
Anders Dahl
(
Technical University of Denmark
)
Collaboration on analysis of 3D image data the QIM Center
Anders Dahl
(
Technical University of Denmark
)
11:15 - 12:00
12:00
A data-driven approach in Astrophysics
-
Iary Davidzon
(
NBI/Cosmic Dawn Center
)
A data-driven approach in Astrophysics
Iary Davidzon
(
NBI/Cosmic Dawn Center
)
12:00 - 12:45
12:45
lunch break
lunch break
12:45 - 14:00
14:00
PS1: Themes: ML in hardware, and in Experiment control and design. Example of question to be debated: Making decisions in the flight in how to change instrument configuration
14:00 - 15:30
PS2: Themes: data collection, reduction and analysis. Example of topics of discussion : 1) Exploring noisy data and analyzing large amount of data [ Minimizing the reliance on good training data and biases from training on simulated data] 2) Changes in data taking/content/quality [dealing with experimental uncertainties]
14:00 - 15:30
Friday 15 May 2020
10:00
PS3: Techniques: Unsupervised/reinforced learning. Example of topics to discuss: Structure in running conditions for good/bad data, Outlier detection, Checking if background has several components. Unsupervised learning : remove vs add bias, in organizing information.
10:00 - 11:30
PS4: Techniques: Deep NN. Examples of topics to discuss: Finding optimum in very high dimensional spaces, Finding simpler methods that will work with fewer parameters under many conditions
10:00 - 11:30
11:30
lunch break
lunch break
11:30 - 13:00
13:00
Report from ML in hardware, and in Experiment control and design
-
Alberto Nannarelli
(
DTU
)
Report from ML in hardware, and in Experiment control and design
Alberto Nannarelli
(
DTU
)
13:00 - 13:20
13:30
Report from data collection, reduction and analysisRe
-
Lamar Moore
(
STFC
)
Report from data collection, reduction and analysisRe
Lamar Moore
(
STFC
)
13:30 - 13:50
14:00
Report from: Techniques: Unsupervised/reinforced learning
-
Iary Davidzon
(
NBI/Cosmic Dawn Center
)
Report from: Techniques: Unsupervised/reinforced learning
Iary Davidzon
(
NBI/Cosmic Dawn Center
)
14:00 - 14:20
14:30
Report from Techniques: Deep NN
-
Troels Petersen
(
Niels Bohr Institute
)
Report from Techniques: Deep NN
Troels Petersen
(
Niels Bohr Institute
)
14:30 - 14:50
15:00
Wrap up and ideas for a roadmap
-
Heloisa Bordallo
(
NBI
)
Troels Petersen
(
Niels Bohr Institute
)
Wrap up and ideas for a roadmap
Heloisa Bordallo
(
NBI
)
Troels Petersen
(
Niels Bohr Institute
)
15:00 - 15:30