Name: MCnet Machine Learning School
Start: 2020-06-22T08:05:00+02:00
End: 2020-06-26T18:00:00+02:00
Location: Lund University

MCnet Machine Learning School

from Monday 22 June 2020 (08:05) to Friday 26 June 2020 (18:00)

Monday 22 June 2020
09:00 Welcome from the Organisers - Stefan Prestel Malin Sjödahl
Welcome from the Organisers
- Stefan Prestel
- Malin Sjödahl
09:00 - 09:05
Room: Zoom
09:05 Historical Perspective - Carsten Petersson (Lund University)
Historical Perspective
- Carsten Petersson (Lund University)
09:05 - 09:30
Room: Zoom
09:30 Question Break
Question Break
09:30 - 09:35
Room: Zoom
09:35 General introduction - Mattias Ohlsson
General introduction
- Mattias Ohlsson
09:35 - 10:00
Room: Zoom
10:00 Question Break
Question Break
10:00 - 10:05
Room: Zoom
10:05 General introduction (continued) - Mattias Ohlsson
General introduction (continued)
- Mattias Ohlsson
10:05 - 10:20
Room: Zoom
10:20 Introduction to Machine Learning - Mattias Ohlsson
Introduction to Machine Learning
- Mattias Ohlsson
10:20 - 10:35
Room: Zoom
10:35 Feedback and coffee
Feedback and coffee
10:35 - 10:55
Room: Zoom
10:55 Introduction to Machine Learning (continued) - Mattias Ohlsson
Introduction to Machine Learning (continued)
- Mattias Ohlsson
10:55 - 11:10
Room: Zoom
11:10 The MLP Architecture - Mattias Ohlsson
The MLP Architecture
- Mattias Ohlsson
11:10 - 11:25
Room: Zoom
11:25 Question Break
Question Break
11:25 - 11:30
Room: Zoom
11:30 The MLP Architecture (continued) - Mattias Ohlsson
The MLP Architecture (continued)
- Mattias Ohlsson
11:30 - 12:00
Room: Zoom
12:00 Free time
Free time
12:00 - 13:30
Room: Zoom
13:30 The CNN architecture - Mattias Ohlsson
The CNN architecture
- Mattias Ohlsson
13:30 - 14:00
Room: Zoom
14:00 Question Break
Question Break
14:00 - 14:05
Room: Zoom
14:05 The CNN architecture (continued) - Mattias Ohlsson
The CNN architecture (continued)
- Mattias Ohlsson
14:05 - 14:35
Room: Zoom
Tuesday 23 June 2020
09:00 Welcome - The organizers
Welcome
- The organizers
09:00 - 09:10
Room: Zoom
09:10 Recurrent neural networks - Mattias Ohlsson
Recurrent neural networks
- Mattias Ohlsson
09:10 - 09:40
Room: Zoom
09:40 Question Break
Question Break
09:40 - 09:45
Room: Zoom
09:45 Recurrent neural networks (continued) - Mattias Ohlsson
Recurrent neural networks (continued)
- Mattias Ohlsson
09:45 - 10:15
Room: Zoom
10:15 Coffee break
Coffee break
10:15 - 10:35
Room: Zoom

10:35 Exercise
Exercise
10:35 - 12:00
Room: Zoom

12:00 Free time
Free time
12:00 - 13:30
Room: Zoom

13:30 Tutorial Session 2
Tutorial Session 2
13:30 - 15:00
Room: Zoom

15:00 Free time
Free time
15:00 - 16:45
Room: Zoom
17:00 ML in HEP: preliminaries - Ben Nachmann
ML in HEP: preliminaries
- Ben Nachmann
17:00 - 17:30
Room: Zoom
17:30 Question Break
Question Break
17:30 - 17:35
Room: Zoom
17:35 Deep learning with HEP images - Ben Nachmann
Deep learning with HEP images
- Ben Nachmann
17:35 - 18:05
Room: Zoom
18:05 Question break
Question break
18:05 - 18:25
Room: Zoom

18:25 Deep learning in HEP beyond images
Deep learning in HEP beyond images
18:25 - 18:55
Room: Zoom
Wednesday 24 June 2020
09:00 Welcome - The organizers
Welcome
- The organizers
09:00 - 09:10
Room: Zoom
09:10 Machine learning for image analysis: Recap + Deep Learning for Video and Audio - Niclas Danielsson
Machine learning for image analysis: Recap + Deep Learning for Video and Audio
- Niclas Danielsson
09:10 - 09:35
Room: Zoom Some useful links, in case zoom video sharing is not possible with your connection. We will also post hem in the chat. Here are all the links in the correct order as presented. YOLO v2 detector (intro): https://www.youtube.com/watch?v=VOC3huqHrss Semantic segmentation Cityscapes https://www.youtube.com/watch?v=ATlcEDSPWXY Object Detetection, traffic intersection: https://www.youtube.com/watch?v=F-lWyJ5Trk4 Instance segmentation (YOLACT): https://www.youtube.com/watch?v=0pMfmo8qfpQ Pose estimation on top of Mask RCNN instance segmentation: https://www.youtube.com/watch?v=KYNDzlcQMWA
09:40 Question Break
Question Break
09:40 - 09:45
Room: Zoom
09:45 Machine learning for image analysis: Deep Learning in the Industry and Deployment Platforms - Niclas Danielsson
Machine learning for image analysis: Deep Learning in the Industry and Deployment Platforms
- Niclas Danielsson
09:45 - 10:15
Room: Zoom Some useful links, in case zoom video sharing is not possible with your connection. We will also post hem in the chat. Here are all the links in the correct order as presented. YOLO v2 detector (intro): https://www.youtube.com/watch?v=VOC3huqHrss Semantic segmentation Cityscapes https://www.youtube.com/watch?v=ATlcEDSPWXY Object Detetection, traffic intersection: https://www.youtube.com/watch?v=F-lWyJ5Trk4 Instance segmentation (YOLACT): https://www.youtube.com/watch?v=0pMfmo8qfpQ Pose estimation on top of Mask RCNN instance segmentation: https://www.youtube.com/watch?v=KYNDzlcQMWA
10:15 Feedback and coffee
Feedback and coffee
10:15 - 10:35
Room: Zoom
10:35 Machine learning for image analysis: Introduction to Tensorflow 2 - Niclas Danielsson
Machine learning for image analysis: Introduction to Tensorflow 2
- Niclas Danielsson
10:35 - 11:05
Room: Zoom Some useful links, in case zoom video sharing is not possible with your connection. We will also post hem in the chat. Here are all the links in the correct order as presented. YOLO v2 detector (intro): https://www.youtube.com/watch?v=VOC3huqHrss Semantic segmentation Cityscapes https://www.youtube.com/watch?v=ATlcEDSPWXY Object Detetection, traffic intersection: https://www.youtube.com/watch?v=F-lWyJ5Trk4 Instance segmentation (YOLACT): https://www.youtube.com/watch?v=0pMfmo8qfpQ Pose estimation on top of Mask RCNN instance segmentation: https://www.youtube.com/watch?v=KYNDzlcQMWA
11:05 Question Break
Question Break
11:05 - 11:10
Room: Zoom
11:15 Machine learning for image analysis: Preparing, training, visualizing. - Niclas Danielsson
Machine learning for image analysis: Preparing, training, visualizing.
- Niclas Danielsson
11:15 - 11:45
Room: Zoom
11:45 Feedback and coffee
Feedback and coffee
11:45 - 12:00
Room: Zoom

12:00 Free time
Free time
12:00 - 13:30
Room: Zoom

13:30 Machine Learning for Image Analysis
Machine Learning for Image Analysis
13:30 - 15:30
Room: Zoom

15:30 Free time
Free time
15:30 - 16:45
Room: Zoom
16:45 ML in HEP: Likelihood-free methods for removing distortions - Ben Nachmann
ML in HEP: Likelihood-free methods for removing distortions
- Ben Nachmann
16:45 - 17:15
Room: Zoom
17:15 Break/Free time
Break/Free time
17:15 - 18:15
Room: Zoom
18:15 ML in HEP: Generative models - Ben Nachmann
ML in HEP: Generative models
- Ben Nachmann
18:15 - 18:45
Room: Zoom
18:45 Question break
Question break
18:45 - 18:50
Room: Zoom
18:50 ML in HEP: Uncertainty quantification and anomaly detection - Ben Nachmann
ML in HEP: Uncertainty quantification and anomaly detection
- Ben Nachmann
18:50 - 19:20
Room: Zoom
Thursday 25 June 2020
09:00 Welcome - The organizers
Welcome
- The organizers
09:00 - 09:10
Room: Zoom
09:10 How to GAN LHC events - Anja Butter
How to GAN LHC events
- Anja Butter
09:10 - 09:40
Room: Zoom
09:40 Question Break
Question Break
09:40 - 09:45
Room: Zoom
09:45 How to GAN LHC events (continued) - Anja Butter
How to GAN LHC events (continued)
- Anja Butter
09:45 - 10:15
Room: Zoom
10:15 Feedback and coffee
Feedback and coffee
10:15 - 10:35
Room: Zoom
10:35 Accelerating HEP theory with ML models - Stefano Carrazza
Accelerating HEP theory with ML models
- Stefano Carrazza
10:35 - 11:05
Room: Zoom
11:05 Question Break
Question Break
11:05 - 11:10
Room: Zoom
11:10 Accelerating HEP theory with ML models (continued) - Stefano Carrazza
Accelerating HEP theory with ML models (continued)
- Stefano Carrazza
11:10 - 11:40
Room: Zoom
11:40 Feedback and coffee
Feedback and coffee
11:40 - 12:00
Room: Zoom

12:00 Free time
Free time
12:00 - 13:30
Room: Zoom

13:30 Autoencoders and their applications
Autoencoders and their applications
13:30 - 16:30
Room: Zoom
Friday 26 June 2020
09:00 Welcome - The organizers
Welcome
- The organizers
09:00 - 09:10
Room: Zoom
09:10 Can we "machine learn" the Next Standard Model? - Wolfgang Waltenberger
Can we "machine learn" the Next Standard Model?
- Wolfgang Waltenberger
09:10 - 09:40
Room: Zoom
09:40 Question Break
Question Break
09:40 - 09:45
Room: Zoom
09:45 Can we "machine learn" the Next Standard Model? (continued) - Wolfgang Waltenberger
Can we "machine learn" the Next Standard Model? (continued)
- Wolfgang Waltenberger
09:45 - 10:15
Room: Zoom
10:15 Feedback and coffee
Feedback and coffee
10:15 - 10:35
Room: Zoom
10:35 Towards the autonomous machine learning fueled supply chain. - Malte Tichy
Towards the autonomous machine learning fueled supply chain.
- Malte Tichy
10:35 - 11:05
Room: Zoom
11:05 Question Break
Question Break
11:05 - 11:10
Room: Zoom
11:10 Towards the autonomous machine learning fueled supply chain (continued) - Malte Tichy
Towards the autonomous machine learning fueled supply chain (continued)
- Malte Tichy
11:10 - 11:40
Room: Zoom
11:40 Feedback and coffee
Feedback and coffee
11:40 - 12:00
Room: Zoom

12:00 Free time
Free time
12:00 - 13:30
Room: Zoom
13:30 Bayesian deep probabilistic differentiable programming: A scientific approach to AI - Michael Green
Bayesian deep probabilistic differentiable programming: A scientific approach to AI
- Michael Green
13:30 - 14:00
Room: Zoom
14:00 Question Break
Question Break
14:00 - 14:05
Room: Zoom
14:05 Bayesian deep probabilistic differentiable programming: A scientific approach to AI (continued) - Michael Green
Bayesian deep probabilistic differentiable programming: A scientific approach to AI (continued)
- Michael Green
14:05 - 14:35
Room: Zoom
14:35 Feedback and coffee
Feedback and coffee
14:35 - 14:55
Room: Zoom
14:55 Outlook on ML in HEP - Tilman Plehn
Outlook on ML in HEP
- Tilman Plehn
14:55 - 15:55
Room: Zoom
15:55 Farewell! - The organizers
Farewell!
- The organizers
15:55 - 16:05
Room: Zoom

Choose timezone