Registration at Hotel We will greet students to the school at the Comfort Hotel Malmö Carlsgatan 10 C, 211 20 Malmö, Sweden Location: https://maps.app.goo.gl/fayc5oVwx9WtBgqJ8 Check in at the hotel is possible at all times, in case your room is not yet availble you can store your luggage at the hotel reception.

Welcome and self presentation

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

Short walk in Malmö

Opening session

• Alberto Pace (CERN)
• Annika Annerby Jansson (Region Skane)

Room: Hörsal B2 1st floor

Machine learning methods: L1 Introduction to Statistics

• Toni Sculac (University of Split Faculty of Science (HR))

Room: Hörsal B2 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.

Announcements Room: Hörsal B2

Machine learning methods: L2 Statistics and Machine Learning

• Toni Sculac (University of Split Faculty of Science (HR))

Room: Hörsal B2 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.

Machine learning methods: L3 Classical Machine Learning

• Toni Sculac (University of Split Faculty of Science (HR))

Room: Hörsal B2 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.

Machine Learning methods: excercise 1

• Francesco Vaselli (Scuola Normale Superiore & INFN Pisa (IT))
• Toni Sculac (University of Split Faculty of Science (HR))

Room: Lecture room 5th floor

Machine Learning methods: excercise 2

• Francesco Vaselli (Scuola Normale Superiore & INFN Pisa (IT))
• Toni Sculac (University of Split Faculty of Science (HR))

Room: Lecture room 5th floor

Malmö: from harbor industry to startup-city We will take a walk in the area around the University and discover the history of Malmö and discover the new start up landscape. We will end the walk by having dinner together.

Machine Learning in Accelerator Technologies: Machine Learning for particle accelerators

• Verena Kain (CERN)

Room: Hörsal B2 Main use cases and applications

Machine Learning in Accelerator Technologies: Bayesian Optimisation

• Verena Kain (CERN)

Room: Hörsal B2

Announcements Room: Hörsal B2

Machine Learning Methods: L4 Introduction to Deep Learning

• Francesco Vaselli (Scuola Normale Superiore & INFN Pisa (IT))
• Toni Sculac (University of Split Faculty of Science (HR))

Room: Hörsal B2 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.

Machine Learning Methods: L5 Advanced Deep Learning

• Francesco Vaselli (Scuola Normale Superiore & INFN Pisa (IT))
• Toni Sculac (University of Split Faculty of Science (HR))

Room: Hörsal B2

Machine learning in accelerators: Exercise 1

• Michael Schenk (CERN)
• Verena Kain (CERN)

Room: Lecture room 5th floor

Machine learning in accelerators: Exercise 2

• Verena Kain (CERN)
• Michael Schenk (CERN)

Room: Lecture room 5th floor

Study time or daily sports

Lightning talks - part 1

• Athar Khodabakhsh
• Jaroslaw Szumega (CERN EP-DT-DD, Mines ParisTech (FR))

Room: Hörsal B2 Athar Khodabakhsh - The Value of Naive Questions in Multidisciplinary XAS Research Jaroslaw Szumega - Machine Learning and Autoencoding Techniques in High-Energy Physics Irradiation Experiments

Machine Learning in Accelerators: Introduction to Reinforcement Learning

• Michael Schenk (CERN)

Room: Hörsal B2

Machine Learning in Accelerators: Advanced concepts for Reinforcement Learning

• Verena Kain (CERN)

Room: Hörsal B2

Announcements Room: Hörsal B2

Machine Learning methods: exercise 3

• Toni Sculac (University of Split Faculty of Science (HR))
• Francesco Vaselli (Scuola Normale Superiore & INFN Pisa (IT))

Room: Lecture room 5th floor

Transport by bus from Comfort Hotel to Snogeholm

Destination Snogeholm Canoeing and hiking excursion, including BBQ dinner by the fireplace at the lake of Snogeholm.

Lightning talks - part 2

• Laurence Matthew Wroe (CERN)
• Joao Ramiro
• Giacomo Tangari (Sapienza Universita e INFN, Roma I (IT))

Room: Hörsal B2 Giacomo Tangari - CLEAR, operational status and machine learning opportunities Laurence Matthew Wroe - ML Applications in Compact Electron Linacs Joao Ramiro - Life as a librarian

Machine Learning in Data Analysis: Complex tasks, basic blocks. The importance of primitives in Machine Learning

• Francesco Vaselli (Scuola Normale Superiore & INFN Pisa (IT))

Room: Hörsal B2

Machine learning in Data Analysis: Introduction to Machine Learning for HEP, Anomaly detection and real time applications

• Sofia Vallecorsa (CERN)

Room: Hörsal B2

Announcements Room: Hörsal B2

Group photo Room: Hörsal B2

Machine learning in Data Analysis: The data reconstruction step - a pattern recognition problem

• Sofia Vallecorsa (CERN)

Room: Hörsal B2

Machine learning in Data Analysis: Exercise 1

• Sofia Vallecorsa (CERN)

Room: Lecture room 5th floor

Machine learning in Data Analysis: Exercise 2

• Sofia Vallecorsa (CERN)

Room: Lecture room 5th floor

Machine learning in accelerators: Exercise 3

• Verena Kain (CERN)

Room: Lecture room 5th floor

Study time or daily sports

Machine learning in Data Analysis: Generative Models for HEP

• Sofia Vallecorsa (CERN)

Room: Hörsal B2

Machine learning in Data Analysis: Systematics in ML

• Sofia Vallecorsa (CERN)

Room: Hörsal B2

Announcements Room: Hörsal B2

Machine learning in Data Analysis: Exercise 3

• Sofia Vallecorsa (CERN)

Room: Lecture room 5th floor

Exam Room: Hörsal B2

Closing ceremony

• Alberto Pace (CERN)

Room: Hörsal B2

Sports and leisure time

Departures Room: Hörsal B2