# 138.128 Machine Learning in Physics This course is in all assigned curricula part of the STEOP.\$(function(){PrimeFaces.cw("Tooltip","widget_j_id_21",{id:"j_id_21",showEffect:"fade",hideEffect:"fade",target:"isAllSteop"});});This course is in at least 1 assigned curriculum part of the STEOP.\$(function(){PrimeFaces.cw("Tooltip","widget_j_id_23",{id:"j_id_23",showEffect:"fade",hideEffect:"fade",target:"isAnySteop"});}); 2023S 2022S 2021S

2023S, VU, 3.0h, 5.0EC

## Properties

• Semester hours: 3.0
• Credits: 5.0
• Type: VU Lecture and Exercise
• Format: Hybrid

## Learning outcomes

After successful completion of the course, students are able to intimately understand the "tool" of machine learning and its application to problems in physics.

For a given problem in physics, they will be able to:

• analyze whether Machine Learning is applicable,
• translate the problem into a suitable optimization problem,
• decide which learning algorithm to employ for its solution,
• program simple routines themselves as well as use libraries where applicable, and
• understand and verify the results of the learning procedure.

## Subject of course

We will cover the following topics in the lectures:

1. Simple optimization problems, gradient descent
2. Supervised learning, over-/underfitting, regularization
3. Linear model, singular value decomposition
4. Non-linear models, classification problems
5. Artificial neural networks
6. Unsupervised learning, clustering
7. Low-rank decompositions, principal component analysis

In the exercises, you will then apply these methods to problems from physics, e.g.:

• temperature deblurring of spectral functions
• classification of proton collisions in the LHC
• recognizing magnetic phases in the Ising model

## Teaching methods

The course is made up of about 12 weeks, each consisting of:

• Lecture, where we will introduce the theoretical concepts behind machine learning.  At your option, you can either follow the live lecture or watch the lecture videos totalling around 75 minutes per week.
• Programming exercise, where you are required to apply the material to physics problem.  You can solve and are to hand in the exercise notebooks online via JupyterHub.
• Q&A and discussion session, during which we will discuss the current exercise, previous exercise, and lecture materials, followed by work in groups.

The course starts with a crash course into the Python programming language, which we will then use throughout the semester.

## Mode of examination

Immanent

General Kick-off meeting for elective classes of IFP:  Tuesday, March 7th, 2023, 13:00-14:00, FH HS6

## Course dates

DayTimeDateLocationDescription
Wed17:00 - 18:0001.03.2023 online: https://tuwien.zoom.us/j/67184844489Kick-off meeting
Wed17:15 - 18:4508.03.2023 - 28.06.2023 online: https://discord.gg/mwpvXwU5rnQ&A session
Fri13:00 - 15:0010.03.2023 - 23.06.2023Hörsaal 6 - RPL 138.128 VU Machine Learning in Physics
Tue16:00 - 19:0027.06.2023FH 8 Nöbauer HS - MATH 138.128 Machine Learning in Physics - Exam
Machine Learning in Physics - Single appointments
DayDateTimeLocationDescription
Wed01.03.202317:00 - 18:00 online: https://tuwien.zoom.us/j/67184844489Kick-off meeting
Wed08.03.202317:15 - 18:45 online: https://discord.gg/mwpvXwU5rnQ&A session
Fri10.03.202313:00 - 15:00Hörsaal 6 - RPL 138.128 VU Machine Learning in Physics
Wed15.03.202317:15 - 18:45 online: https://discord.gg/mwpvXwU5rnQ&A session
Fri17.03.202313:00 - 15:00Hörsaal 6 - RPL 138.128 VU Machine Learning in Physics
Wed22.03.202317:15 - 18:45 online: https://discord.gg/mwpvXwU5rnQ&A session
Fri24.03.202313:00 - 15:00Hörsaal 6 - RPL 138.128 VU Machine Learning in Physics
Wed29.03.202317:15 - 18:45 online: https://discord.gg/mwpvXwU5rnQ&A session
Fri31.03.202313:00 - 15:00Hörsaal 6 - RPL 138.128 VU Machine Learning in Physics
Wed19.04.202317:15 - 18:45 online: https://discord.gg/mwpvXwU5rnQ&A session
Fri21.04.202313:00 - 15:00Hörsaal 6 - RPL 138.128 VU Machine Learning in Physics
Wed26.04.202317:15 - 18:45 online: https://discord.gg/mwpvXwU5rnQ&A session
Fri28.04.202313:00 - 15:00Hörsaal 6 - RPL 138.128 VU Machine Learning in Physics
Wed03.05.202317:15 - 18:45 online: https://discord.gg/mwpvXwU5rnQ&A session
Fri05.05.202313:00 - 15:00Hörsaal 6 - RPL 138.128 VU Machine Learning in Physics
Wed10.05.202317:15 - 18:45 online: https://discord.gg/mwpvXwU5rnQ&A session
Fri12.05.202313:00 - 15:00Hörsaal 6 - RPL 138.128 VU Machine Learning in Physics
Wed17.05.202317:15 - 18:45 online: https://discord.gg/mwpvXwU5rnQ&A session
Wed24.05.202317:15 - 18:45 online: https://discord.gg/mwpvXwU5rnQ&A session
Fri26.05.202313:00 - 15:00Hörsaal 6 - RPL 138.128 VU Machine Learning in Physics

## Examination modalities

Requirements for this class are:

1. weekly coding exercises, where you will appliy ML concepts to simple problems. Each exercise has equal weight (70 per cent of the grade).
2. a written test, where you will have to demonstrate that you understood the concepts (30 per cent of the grade).

Attendance at the weekly Q&A sessions is recommended, but not required.

Grading scheme:  "Genügend" requires above 1/2, "Befriedigend" requires 2/3, "Gut" requires 4/5, "Sehr gut" requires 9/10 of points.  No further point cutoffs.

There is a substitute test.  If you choose to partake in it, it will replace the marks of your test.

## Course registration

Begin End Deregistration end
21.02.2023 10:30 05.03.2023 23:00 05.03.2023 23:00

## Curricula

Study CodeObligationSemesterPrecon.Info
033 261 Technical Physics Mandatory elective
066 460 Physical Energy and Measurement Engineering Not specified
066 460 Physical Energy and Measurement Engineering Not specified
066 461 Technical Physics Not specified