Module 39-Inf-ML Introduction to Machine Learning

Faculty

Faculty of Technology

Person responsible for module

Frau Prof'in Dr. Barbara Hammer

Regular cycle (beginning)

Every winter semester

Credit points and duration

5 Credit points

For information on the duration of the modul, refer to the courses of study in which the module is used.

Competencies

Non-official translation of the module descriptions. Only the German version is legally binding.

The students gain competences to analyse, formalize and treat a learning problem with appropriate methods and to judge algorithms with respect to their suitability for a given problem. In exercises, methods are applied to concrete and practical application problems, partially in form of programming tasks.

Content of teaching

The lecture introduces basic principles and theories of machine learning and formalizes learning problems. Fundamental mathematical and statistical methods are discussed and standard algorithms are presented including parameter estimation, Bayesian methods, linear approaches. Further topics are the basic notions of machine learning like training, test and validation, generalization, overfitting, model selection, regularization and the bias vs. variance dilemma.

Recommended previous knowledge

Knowledge as in the module 39-Inf-13

Necessary requirements

Prerequisite modules:
Successful completion of the modules 39-Inf-1 Algorithms and Data Structures, 24-M-INF1 Mathematics for Informatics I and 24-M-INF2 Mathematics for Informatics II
OR
Successful completion of the modules 39-Inf-PP Principles of Programming, 24-M-INF1_a Mathematics for Computer Science I (or 24-M-INF1_a_ub) and 24-M-INF2_a Mathematics for Computer Science II.

In the Master's degree programmes "Data Science" and "Biomechatronics", these requirements are deemed to have been met upon successful admission to the Master's degree programme.

Explanation regarding the elements of the module

Module structure: 1 bPr ¹

Courses

Introduction to Machine Learning

Type exercise

Regular cycle WiSe

Workload⁵ 30 h (15 + 15)

LP 1

Introduction to Machine Learning

Type lecture

Regular cycle WiSe

Workload⁵ 60 h (30 + 30)

LP 2

Examinations

portfolio with final examination

Allocated examiner Person responsible for module examines or determines examiner

Weighting 1

Workload 60h

LP² 2

Portfolio of homework assignments accompanying the lecture, usually given weekly, and final written exam (ca. 60 min) or oral exam (15 - 25 min).
The assignments complement and deepen the content of the lecture.
Proof of a sufficient amount of correctly solved assignments (50% of the maximum total score in the semester). The final exam covers the content of the lecture and the assignments.

The exam can be alternatively conducted as an e-exam, open-book exam, or e-open-book exam. In the case of an open-book exam and an e-open-book exam, the duration is 120-180 minutes.

The module is used in these degree programmes:

Degree programme	Version	Profile	Recommended start ³	Duration	Mandatory option ⁴
Bioinformatics and Genome Research / Bachelor of Science [FsB vom 30.09.2016 mit Änderungen vom 15.09.2017, 02.05.2018, 01.07.2019 und 16.08.2021]	Bachelor with One Core Subject (Academic)		5.	one semester	Compulsory optional subject
BioMechatronics / Master of Science [Studien- und Prüfungsordnung vom 22.12.2022]			1. o. 2. o. 3.	one semester	Compulsory optional subject
Data Science / Master of Science [FsB vom 06.04.2018 mit Änderungen vom 01.07.2019, 02.03.2020, 21.03.2023 und 10.12.2024]		Variante 1	1.	one semester	Obligation
Fundamentals of Cognitive Systems / Bachelor [FsB vom 16.05.2023]	Minor Subject (Academic), 60 CPs		3. o. 5.	one semester	Obligation
Fundamentals of Cognitive Systems / Bachelor [FsB vom 04.06.2020]	Minor Subject (Academic), 60 CPs		3.	one semester	Obligation
Informatics / Bachelor of Science [FsB vom 01.04.2025]	Major Subject (Academic)	Modelling	5.	one semester	Obligation
Informatics / Bachelor [FsB vom 01.04.2025]	Minor Subject (Academic), 60 CPs		3. o. 5.	one semester	Compulsory optional subject
Informatics / Bachelor of Science [FsB vom 16.05.2023 mit Änderung vom 01.08.2023]	Major Subject (Academic)	Modelling	5.	one semester	Obligation
Informatics / Bachelor [FsB vom 16.05.2023 mit Änderung vom 01.08.2023]	Minor Subject (Academic), 60 CPs	Practical Informatics	5.	one semester	Compulsory optional subject
Informatics / Bachelor [FsB vom 16.05.2023 mit Änderung vom 01.08.2023]	Minor Subject (Academic), 60 CPs	Technical Informatics	5.	one semester	Compulsory optional subject
Informatics / Bachelor of Science [FsB vom 04.06.2020 mit Änderung vom 15.12.2021]	Major Subject (Academic)	Technical Informatics	5.	one semester	Compulsory optional subject
Intelligent Systems / Master of Science [FsB vom 27.07.2018 mit Änderung vom 04.06.2020]			1.	one semester	Compulsory optional subject
Cognitive Informatics / Bachelor of Science [FsB vom 30.09.2016 mit Änderungen vom 15.09.2017, 02.05.2018, 01.07.2019 und 16.08.2021]	Bachelor with One Core Subject (Academic)		3.	one semester	Obligation
Artificial Intelligence and Cognitive Informatics / Bachelor of Science [FsB vom 16.05.2023 mit Änderung vom 01.04.2025]	Bachelor with One Core Subject (Academic)		3. o. 5.	one semester	Obligation
Medical Physics / Bachelor of Science [FsB vom 28.03.2024]	Bachelor with One Core Subject (Academic)	Strukturierte Ergänzung des fw 1-Fach-Ba: Bereich Informatik	5.	one semester	Compulsory optional subject
Informatics for the Natural Sciences / Master of Science [FsB vom 30.09.2016 mit Berichtigung vom 10.01.2017 und Änderungen vom 15.09.2017, 02.05.2018, 04.06.2020 und 31.03.2023]			1.	one semester	Compulsory optional subject

Automatic check for completeness

The system can perform an automatic check for completeness for this module.

Previus version of this module

39-Inf-ML_ver1 Introduction to Machine Learning

Legend

1: The module structure displays the required number of study requirements and examinations.
2: LP is the short form for credit points.
3: The figures in this column are the specialist semesters in which it is recommended to start the module. Depending on the individual study schedule, entirely different courses of study are possible and advisable.
4: Explanations on mandatory option: "Obligation" means: This module is mandatory for the course of the studies; "Optional obligation" means: This module belongs to a number of modules available for selection under certain circumstances. This is more precisely regulated by the "Subject-related regulations" (see navigation).
5: Workload (contact time + self-study)
SoSe: Summer semester
WiSe: Winter semester
SL: Study requirement
Pr: Examination
bPr: Number of examinations with grades
uPr: Number of examinations without grades
: This academic achievement can be reported and recognised.