IMPRS / Origins Data Science Block Course

Europe/Berlin
Description

The Origins Data Science Lab (ODSL) and the International Max Planck Research School on Elementary Particle Physics (IMPRS) is organizing a block course on "Introduction to Machine Learning" targeted towards PhD students in physics. Interested MSc students from LMU and TUM are welcome as well.

The courses will take place in person at the MPP building at  Forschungszentrum Garching. The lectures and tutorials will take place in person in the Alps room (A.1.01/03) which is the main auditorium located on the first floor of the MPP. After entering the building via its main entrance on the Boltzmannstrasse, please take the stairs to the right of the Heisenberg cafe to get to the first floor. When reaching the first floor, the main auditorium is directly on the right hand side and facing the Boltzmannstrasse.

Note that the automatic glass main entrance works only until 4:00 PM. Thus, for the sessions starting at 4:00 PM it will be recommended to enter the building already at 3:50 PM.

The two-week introductory block course (15.04.2023 - 25.04.2023) will cover the following topics:

  • First Week:
    • Linear models, supervised learning 
    • Machine Learning theory (bias / variance trade-off)
    • Classical clustering algorithms
    • Boosted Decision Trees
    • Intro to Neural Networks (universal approximation theorem, optimizers)
    • Automatic differentiation, deep learning frameworks (e.g, pytorch)
       
  • Second Week:
    • Convolutional Neural Networks (grid-based models)
    • Sequence-based models and Transformers
    • Geometric Deep Learning and Graph Neural Networks 
    • Deep Generative Models
       

Please Register for the Event using the Registration Link.

With lecturers:

  • Nicole Hartman, nicole.hartman@tum.de
  • Baran Hashemi, baran.hashemi@origins-cluster.de

Repository with Exercises: GitHub

Forms of credit: This semester there will be no official ECTS credits. We'll have time for tutorials with tutors available to help work through the solutions, but there is not a need to submit these tutorials for a course grade. Certificates of participation may be provided on request.

Zoom connection

https://tum-conf.zoom-x.de/j/63431946615?pwd=cm9JZWdLSmVJRU50cjRLSFNubndFdz09

Meeting ID: 634 3194 6615

Passcode: 443046

 

 

Registration
Participants
Participants
  • Aleksandra Grudskaia
  • Alena Khokhriakova
  • Alessandro Ratti
  • Ana Bacelj
  • Anik Halder
  • Anisha Anisha
  • Aparna Sankar
  • Avalon Rego
  • Benedikt Wach
  • Boris Betancourt Kamenetskaia
  • Brennan Hackett
  • Chiara Leonhardt
  • Christian Biello
  • Claudia Toci
  • Cole Johnston
  • Dandi Zhang
  • Daniel Karner
  • Elena Viscardi
  • Eleonora Bianchi
  • Elia Mazzucchelli
  • Emma Chizzali
  • Fabian Wagner
  • Fabio Novissimo
  • Felix Hagemann
  • Giacomo Contri
  • Giorgio Pirola
  • Hanieh Zandinejad
  • HeeSu Byum
  • Ivana Bab
  • Ivana Nikolac
  • Jakob Ehring
  • Jakob Linder
  • Jana Grupa
  • Jarred Green
  • Jaydeep Govind Kandekar
  • Joanne Tan
  • Jonathan Schubert
  • Joy Sanghavi
  • Ka Hei Choi
  • Laura Di Federico
  • Ludwig Burger
  • Luise Meyer-Hetling
  • Marija Minzburg
  • Marius Wiesemann
  • Marta Monelli
  • Maryam Tajalli
  • Moh Ashari
  • Nandini Jain
  • Paula Sanchez Saez
  • Payam Vaghefi
  • Peter Hinderberger
  • Qiang Wang
  • Robert Willer
  • Safak Celik
  • Sagar Hazra
  • Sankalp Choudhuri
  • Sijin Chen
  • Silas Zelmer
  • Storm Feng Lin
  • Surya Shivaprasad
  • Teresa Braun
  • Tobias Preis
  • Ulrich Walter
  • Valeriya Korol
  • Vyoma Muralidhara
  • Yunhe Wang
  • Zeynep Su Selcuk