Skip to content
Technische Universität Berlin Deutsch
Course catalog and module transfer system

Julia for Machine LearningModule description #41144 / Version 2

← Module page Deutsche Fassung
This module description is not valid in the current semester (Winter semester 2026/27). Current version (v3)
Module / Version#41144 / #2
ValiditySummer semester 2024 – Summer semester 2024
Available language(s)English
Credit points6
Person responsible for the moduleMüller, Klaus-Robert
GradingGraded
Exam formatPortfolio examination
Language(s) of instructionEnglish

Affiliation

FacultyFakultät IV
InstituteInstitut für Softwaretechnik und Theoretische Informatik
Academic chair34352000 FG Maschinelles Lernen

Contact

OfficeFR 6-1
Contact personHill, Adrian Rainer
E-mail addresshill@tu-berlin.de
Websitehttps://web.ml.tu-berlin.de/teaching/courses/

Learning outcomes

The students are able to use the Julia programming language to implement and apply machine learning algorithms. They are familiar with common packages in the Julia ecosystem for classical machine learning, deep learning, and data visualizations. Students have a thorough understanding of automatic differentiation and the ways automatic differentiation packages differ in implementation. They are familiar with best practices for Julia development and can write reproducible, unit-tested code.

Content

In the first half of the course, students learn fundamentals of the Julia programming language as well as packages in the wider Julia Machine Learning ecosystem:
- Performant array processing and linear algebra (LinearAlgebra.jl)
- Working with tabular data and preprocessing features (DataFrames.jl)
- Creating visualizations and plots (Plots.jl, StatsPlots.jl)
- Classical Machine Learning algorithms (MLJ.jl)
- Mathematical fundamentals of automatic differentiation
- Differences in implementations of automatic differentiation in Julia (ChainRules.jl, Zygote.jl, Enzyme.jl, ForwardDiff.jl, FiniteDifferences.jl)
- Training Deep Learning models (Flux.jl, MLDatasets.jl)
- Common development workflows for package development and scientific experiments (PkgTemplates.jl, DrWatson.jl)
- Best practices for Julia development, profiling, and debugging (Debugger.jl, Infiltrator.jl, ProfileView.jl, Cthulhu.jl)

In the second half, student work in groups on a small programming project of their choice, learning how to:
- Structure and develop a package
- Write package tests
- Write and host package documentation

Module components

Compulsory area

The following courses are mandatory for this module:

CoursesTypeNumberFrequencyLanguageHours per weekCourse catalog
Julia for Machine LearningIntegrated course Winter and summer semester[de]4 ISIS

Courses in the course catalog

Courses created from the teaching units of this module.

Winter semester 2026/27 (1)

Julia for Machine Learning (Integrated course) 1

All groups of this course in the catalog

Workload and credit points

Julia for Machine Learning (Integrated course)

Workload descriptionMultiplierHoursTotal
Homework, including follow-up on lectures42 h8 h
Project work (programming, follow-up on code reviews, preparation of presentation)1144 h144 h
Project presence time (project selection meeting, 2 code reviews, presentations)42 h8 h
Lectures102 h20 h
180 h

The workload of the module adds up to 180 hours. The module therefore comprises 6 credit points.

Description of teaching and learning methods

The module is divided into two parts: In the first half of the semester, weekly lectures are held to teach the basics of the Julia programming language and packages from its machine learning ecosystem. Based on these lectures, weekly programming homework is given in the form of guided notebooks to be solved individually by students.

In the second half of the semester, students work in small groups on programming projects of their choice, learning best practices for package development in Julia. During code review sessions, students give each other feedback on their projects before presenting their work in end-of-semester presentations.

Requirements for participation and examination

Desirable prerequisites for participation in the courses:

This course assumes knowledge of common programming concepts like for-loops and arrays.
No knowledge of the Julia programming language is required.

Knowledge of basic mathematical concepts is helpful. For example, knowledge of linear algebra helps understand array operations.

Mandatory requirements for the module examination registration:

This module has no examination requirements.

Completion of the module

GradingGraded
Exam formatPortfolio examination
Type of portfolio examination100 points in total
LanguageEnglish

Test elements

NamePoints/WeightCategoryDuration/Extent
(Deliverable assessment) Homework20practical4 homework notebooks, each with a workload of 2 hours
(Deliverable assessment) Project work50practicalProgramming project: implement and document a software package in Julia
(Examination) Presentation10oral10-minute presentation of project work to other students + 5 minutes of questions and answers
(Examination) Oral exam: evaluation of the project20oral20-minute oral exam and evaluation of the programming project

Duration of the module

The following number of semesters is estimated for taking and completing the module: 1 semester(s).

This module can be started in the following semesters: Winter and summer semester.

Maximum number of participants

The maximum capacity of participants is 40.

Registration procedures

Please check the module's website (to be found at the website of the Machine Learning Group at TU Berlin).

Recommended reading, lecture notes

Lecture notes

unavailable

Electronic lecture notes

available

Recommended literature

No recommended literature given

Assigned programs

This module is not used in any program.

Miscellaneous

Not specified