Machine Learning for Molecular Physics WiSe 24/25

Instructors: 

Prof. Cecilia Clementi <cecilia.clementi@fu-berlin.de>

Dr. Lorenzo Giambagli <giambagli@fu-berlin.de>

Tutor:

Max Schebek <m.schebek@fu-berlin.de>

Lectures: Tuesdays 14:00-16:00 - 1.4.03 Seminarraum T2 (Arnimallee 14)

Tutorials: Tuesdays 16:00-18:00 - 1.4.03 Seminarraum T2 (Arnimallee 14) 

First day of lectures: October 15, 2023

Last day of lectures: February 11, 2024

First tutorial: October 22, 2023

Winter break: December 21, 2023 - January 5, 2024

 

Exams: February 25, 2025 h14:00 Conference Room Arnimallee 12 (Theoretical & Computational Biophysics - AI4Science Building). Group presentation on a topic agreed upon with the teachers, where each member should speak for approximately 15 minutes. Questions related to the project and all course topics may be asked.

 

CHAT ROOM: 

TBA

You need an account in Physics to be able to join the chat. Please ask ZEDV (zedv@physik.fu-berlin.de) to give you an account in Physics if you do not have one already.

Requirements:

  • Basic stat mech
  • Knowledge of computational methods for molecular simulations; MD, MC
  • Basic knowledge in solid state physics
  • Basic programming in python or related
Suggested Textbooks:

Deep Learning Foundations and Concepts (2024), Chris Bishop, Hugh Bishop online version here

Deep Learning (2016), Ian Goodfellow, Yoshua Bengio, Aaron Courville online version here

Lecture content:

  1. 15.10.: Organizational meeting
  2. 22.10.: Computer science I - Intro to machine learning
  3. 29.10.: Computer science II - Intro to machine learning
  4. 05.11.: Computer science III - Deep Learning Architectures I
  5. 12.11.: Computer science III - Deep Learning Architectures II
  6. 19.11.: Dimensionality reduction and reaction coordinates
  7. 26.11.: Featurization of molecular systems
  8. 03.12.: ML potentials I
  9. 10.12.: ML potentials II
  10. 17.12.: ML potentials III
  11. 07.01.: ML for coarse-grained potentials
  12. 14.01.: Diffusion Models
  13. 21.01.: Physical Interpretation of ML Models I
  14. 28.01.: Physical Interpretation of ML Models II
  15. 04.02.: Project Development
  16. 11.02.: Project Development