Thematic CERN School of Computing on Machine Learning 2024

Name: Thematic CERN School of Computing on Machine Learning 2024
Start: 2024-10-13T15:00:00+02:00
End: 2024-10-19T11:00:00+02:00
Location: MedILS, Split, Croatia

13 Oct 2024, 15:00 → 19 Oct 2024, 11:00 Europe/Zurich

MedILS, Split, Croatia

Meštrovićevo šetalište 45 HR – 21000 Split Croatia

Alberto Pace (CERN), Andrzej Nowicki (CERN), Kristina Gunne (CERN)

Description

The 15th Thematic CERN School of Computing (tCSC Machine Learning 2024) will take place on October 13-19, 2024.

The school will focus on the theme of Machine Learning and Artificial Intelligence applied to Data Analysis and Accelerator Technology. The programme will offer 22 hours of lectures and hands-on exercises, and student presentation sessions.

This school is organized by CERN in collaboration with the Faculty of Science, University of Split. The school will take place in Split, Croatia, and be hosted at the Mediterranean Institute For Life Sciences (MEDILS) Conference Centre. The Centre is a historical renovated building situated in a wooded and landscaped park located on the Adriatic Sea coast, a few kilometers from the centre of Split.

Important dates 2024

8 May application opens
19 June application close
3 July invitations sent to selected students
4 September participation fee deadline

CERN School of ComputingContact

Computing.School@cern.ch

Sunday 13 October
- 15:00 → 16:00
  
  Registration at MedILS 1h
- 17:30 → 17:45
  
  Transport to Split 15m
- 18:00 → 19:15
  
  Guided tour of Split 1h 15m
- 19:30 → 21:30
  
  Welcome dinner at Restoran Para di šoto 2h
Monday 14 October
- 08:45 → 09:45
  
  opening session 1h
  
  Speaker: Alberto Pace (CERN)
  
  2024-10-14-School-Presentation-ML-Split-v03-Monday.pdf
  
  2024-10-14-School-Presentation-ML-Split-v03-Monday.pptx
- 09:45 → 10:45
  
  Machine learning methods: L1 Introduction to Statistics 1h
  
  In this lecture we will go over key concepts in statistics which are the cornerstone of mathematical foundation of Machine Learning. We will define frequentistic and Bayesian probabilities, learn what is a PDF. We will also discuss parameter estimation with the Maximum Likelihood method and finish with the definition of Confidence Intervals.
  
  Speaker: Toni Sculac (University of Split Faculty of Science (HR))
  
  Lecture_1_tCSC2024.pdf
- 10:45 → 11:00
  
  Announcements 15m
  
  tCSC School logistics and updates.pdf
  
  tCSC School logistics and updates.pptx
- 11:00 → 11:30
  
  Coffee 30m
- 11:30 → 12:30
  
  Machine learning methods: L2 Statistics and Machine Learning 1h
  
  We start this lecture with unfolding and hypothesis testing, another two key concepts from statistics. Key part of the lecture is the Neyman-Person lemma that paves a clear path for the needs of Machine Learning in statistics.
  
  Speaker: Toni Sculac (University of Split Faculty of Science (HR))
  
  Lecture_2_tCSC2024.pdf
- 12:30 → 13:30
  
  Lunch 1h
- 13:30 → 15:15
  
  Study time or daily sports 1h 45m
- 15:15 → 15:45
  
  Coffee 30m
- 15:45 → 16:45
  
  Machine learning methods: L3 Classical Machine Learning 1h
  
  We continue tackling the problem of trying to know the likelihood ratio with the use of Classical Machine Learning. We try to solve it by brute force and then we move to Machine Learning techniques. We start with a Kernel Density Estimators. We continue by defining what is a decision tree, what is a leaf and we study how it works on a very simple example. We go further and explain the difference between classification and regression, as well as the need for pruning, bagging, and boosting. This main goal of this lecture is to remove the idea of the “black-box approach" and understand all of the details of a decision tree.
  
  Speaker: Toni Sculac (University of Split Faculty of Science (HR))
  
  Lecture_3_tCSC2024.pdf
- 16:45 → 17:00
  
  Break 15m
- 17:00 → 18:00
  
  Machine Learning methods: excercise 1 1h
  
  Speakers: Francesco Vaselli (Scuola Normale Superiore & INFN Pisa (IT)), Toni Sculac (University of Split Faculty of Science (HR))
  
  dataA.csv
  
  solutions1.ipynb
  
  tCSC_MachineLearning_Exercise_Instructions.pdf
  
  tCSC_ml_set_1.pdf
  
  tCSC solution1.pdf
- 18:00 → 19:00
  
  Machine Learning methods: excercise 2 1h
  
  Speakers: Francesco Vaselli (Scuola Normale Superiore & INFN Pisa (IT)), Toni Sculac (University of Split Faculty of Science (HR))
  
  dataA.csv
  
  dataB.csv
  
  solutions2.ipynb
  
  tCSC_MachineLearning_Exercise_Instructions.pdf
  
  tCSC_ml_set_2-1.pdf
- 19:30 → 20:30
  
  Dinner at MedILS 1h
Tuesday 15 October
- 08:45 → 09:45
  
  Machine Learning in Accelerator Technologies: Machine Learning for particle accelerators 1h
  
  Main use cases and applications
  
  Speaker: Verena Kain (CERN)
  
  Lecture_1_vkain_intro.pdf
- 09:45 → 10:45
  
  Machine Learning in Accelerator Technologies: Bayesian Optimisation 1h
  
  Speaker: Verena Kain (CERN)
  
  Lecture_2_vkain_BO.pdf
- 10:45 → 11:00
  
  Announcements 15m
- 11:00 → 11:30
  
  Coffee 30m
- 11:30 → 12:30
  
  Machine Learning Methods: L4 Introduction to Deep Learning 1h
  
  We introduce the concept of a Neural Network (NN) and study their application with a single-neuron network. This again allows us to avoid the "black-box approach" and really understand the key concepts of how a NN works. We discuss activation functions and how the NN learns with the help of the loss functions and backpropagation. We finish by discussing the basic idea of a Deep Neural Network and basic training concepts.
  
  Speakers: Francesco Vaselli (Scuola Normale Superiore & INFN Pisa (IT)), Toni Sculac (University of Split Faculty of Science (HR))
  
  DeepNN.ipynb
  
  Lecture_4_tCSC2024.pdf
- 12:30 → 13:30
  
  Lunch 1h
- 13:30 → 15:15
  
  Study time or daily sports 1h 45m
- 15:15 → 15:45
  
  Coffee 30m
- 15:45 → 16:45
  
  Machine Learning Methods: L5 Advanced Deep Learning 1h
  
  Speakers: Francesco Vaselli (Scuola Normale Superiore & INFN Pisa (IT)), Toni Sculac (University of Split Faculty of Science (HR))
  
  Link to slides
  
  Link to slides
  
  ml CSC .pdf
- 16:45 → 17:00
  
  Break 15m
- 17:00 → 18:00
  
  Machine learning in accelerators: Exercise 1 1h
  
  Speakers: Michael Schenk (CERN), Verena Kain (CERN)
  
  Ex1.ipynb
  
  Ex2.ipynb
  
  Ex3.ipynb
  
  Exercises_ML4acc.pdf
- 18:00 → 19:00
  
  Machine learning in accelerators: Exercise 2 1h
  
  Speakers: Michael Schenk (CERN), Verena Kain (CERN)
  
  Exercises_ML4acc.pdf
- 19:30 → 20:30
  
  Dinner at MedILS 1h
Wednesday 16 October
- 08:45 → 09:45
  
  Machine Learning in Accelerators: Introduction to Reinforcement Learning 1h
  
  Speaker: Michael Schenk (CERN)
  
  rl_intro_161024.pdf
  
  rl_intro_161024.pptx
- 09:45 → 10:45
  
  Machine Learning in Accelerators: Advanced concepts for Reinforcement Learning 1h
  
  Speaker: Verena Kain (CERN)
  
  Lecture_4_vkain_advancedRL.pdf
- 10:45 → 11:00
  
  Announcements 15m
- 11:00 → 11:15
  
  Coffee 15m
- 11:15 → 12:15
  
  Machine Learning methods: exercise 3 1h
  
  Speakers: Francesco Vaselli (Scuola Normale Superiore & INFN Pisa (IT)), Toni Sculac (University of Split Faculty of Science (HR))
  
  dataA.csv
  
  dataB.csv
  
  dataC.csv
  
  solutions3a.ipynb
  
  solutions3b.ipynb
  
  tCSC_MachineLearning_Exercise_Instructions.pdf
  
  tCSC_ml_set_3a.pdf
  
  tCSC_ml_set_3b.pdf
- 12:15 → 13:00
  
  Lunch 45m
- 13:00 → 18:30
  
  River rafting excursion 5h 30m
  
  Departure from MedILS at 13h
- 18:30 → 21:00
  
  Dinner at Kastel Slanica Omis 2h 30m
- 21:00 → 21:45
  
  Transport back to medILS 45m
Thursday 17 October
- 08:45 → 09:45
  
  Machine learning in Data Analysis: Introduction to Machine Learning for HEP, Anomaly detection and real time applications 1h
  
  Speaker: Dr Sofia Vallecorsa (CERN)
  
  CSC24_Lecture1_Intro_Architectures.pdf
- 09:45 → 10:45
  
  Machine learning in Data Analysis: The data reconstruction step - a pattern recognition problem 1h
  
  Speaker: Dr Sofia Vallecorsa (CERN)
  
  CSC24_Lecture2_use_cases.pdf
- 10:45 → 11:00
  
  Announcements 15m
- 11:00 → 11:05
  
  Group photo 5m
- 11:05 → 11:30
  
  Coffee 25m
- 11:30 → 12:30
  
  Machine learning in Data Analysis: Generative Models for HEP 1h
  
  Speaker: Ilaria Luise (CERN)
  
  CSC24_Lecture3_foundation_models.pdf
- 12:30 → 13:30
  
  Lunch 1h
- 13:30 → 15:15
  
  Study time or daily sports 1h 45m
- 15:15 → 15:45
  
  Coffee 30m
- 15:45 → 16:45
  
  Machine learning in accelerators: Exercise 3 1h
  
  Speaker: Verena Kain (CERN)
  
  Ex4.ipynb
  
  Ex5.ipynb
  
  rl_awake_ex.pdf
  
  rl_awake_ex.pptx
- 16:45 → 17:00
  
  Break 15m
- 17:00 → 18:00
  
  Machine learning in Data Analysis: Exercise 1 1h
  
  Speakers: Ilaria Luise (CERN), Dr Sofia Vallecorsa (CERN)
  
  CSC24_exercises.pdf
  
  link to dl4phys
- 18:00 → 19:00
  
  Machine learning in Data Analysis: Exercise 2 1h
  
  Speakers: Ilaria Luise (CERN), Dr Sofia Vallecorsa (CERN)
- 19:30 → 20:30
  
  Dinner 1h
Friday 18 October
- 08:45 → 09:45
  
  Lightning talks 1h
  
  01_AndreaPaccagnela.pdf
  
  02_YanxiGu.pdf
  
  03_AlbertoPimpo.pdf
  
  04_JoelWulff.pdf
  
  04_JoelWulff.pptx
  
  06_VeronicaKirsebom.pdf
  
  08_Luka
  
  09_NikolinaBunijevac.pdf
  
  09_NikolinaBunijevac.pptx
- 09:45 → 10:45
  
  Machine learning in Data Analysis: Systematics in ML 1h
  
  Speaker: Ilaria Luise (CERN)
  
  CSC24_Lecture4_Systematics_ML.pdf
- 10:45 → 11:00
  
  Announcements 15m
- 11:00 → 11:30
  
  Coffee 30m
- 11:30 → 12:30
  
  Machine learning in Data Analysis: Exercise 3 1h
  
  Speakers: Ilaria Luise (CERN), Dr Sofia Vallecorsa (CERN)
  
  CSC24_Lecture5_Extra_Material.pdf
- 12:30 → 13:30
  
  Lunch 1h
- 13:30 → 14:30
  
  Exam 1h
- 14:30 → 15:00
  
  Break 30m
- 15:00 → 16:00
  
  Closing ceremony 1h
  
  Speaker: Alberto Pace (CERN)
- 16:00 → 18:00
  
  Sports and leisure time 2h
- 19:30 → 21:30
  
  Closing dinner in Restaurant Kavanazona 2h Restaurant Kavanazona
  
  Restaurant Kavanazona
Saturday 19 October
- 08:00 → 11:00
  
  Departures from MedILS 3h

Choose timezone

Thematic CERN School of Computing on Machine Learning 2024

MedILS, Split, Croatia

Restaurant Kavanazona