Moses - Uncertainty in Machine Learning

Display language

Diese Modulbeschreibung gilt nicht im aktuellen Semester.

Die Modulbeschreibung gilt nur für den Zeitraum WiSe 2023/24 - WiSe 2023/24. Die Version für das aktuelle Semester (SoSe 2024) finden Sie hier: Modulbeschreibung des SoSe 2024

Module / Version:
#41113 / #2

Validity:
WiSe 2023/24 - WiSe 2023/24

Default display language:
English

Module title:
Uncertainty in Machine Learning

Credits:
3

Responsible person:
Haufe, Stefan

Grading:
benotet

Type of exam:
Portfolioprüfung

Zugehörigkeit

Faculty:
Fakultät IV

Institute:
Institut für Softwaretechnik und Theoretische Informatik

Area of expertise:
34352700 FG S-Professur Unsicherheit, inverse Modellierung und maschinelles Lernen

Prüfungsausschuss:
No information

Kontakt

Office:
MAR 4-4

Contact person:
Panknin, Danny

E-mail address:
danny.panknin@tu-berlin.de

Website:

http://tu.berlin/uniml

Learning Outcomes

Knowledge: Students have obtained an extensive overview of the manifold aspects of uncertainty in machine learning, with individual deep insights into a topic of choice. Skills: Students have acquired or refined skills to independently review and systematically structure scientific literature and have gained experience in presenting their literature research to a critical audience as well as in participating in scientific discussions. Competencies: Students are able to critically reflect on novel scientific results in the scope of uncertainty in machine learning. They are able to relate these results to the literature and assess their quality and impact based on adequate metrics.

Content

Metrology in data science and machine learning Fundamental topics in stochastics, probability theory, and statistics - Random variables, probability spaces, probability density functions - Independence, marginalization - Law of large numbers - Central limit theorem - Bayesian inference, priors and posteriors - Confidence and credibility intervals - Bootstrap, Jackknife, method of surrogate data Uncertainty propagation through fixed measurement equations - Guide to the Expression of Uncertainty in Measurement (GUM) - Polynomial chaos - Monte Carlo methods Uncertainty estimation in Machine Learning and Deep Learning - Aleatoric and epistemic uncertainty - Hierarchical and empirical Bayesian models, predictive distribution - Gaussian processes - Errors-in-variables models - Robust regression - Bayesian/Probabilistic Neural Networks - Dropout - Ensemble Methods - Monte Carlo methods - Conformal prediction - Variational inference - Normalizing flows, invertible neural networks, diffusion models Metrics of Uncertainty Calibration - Proper Scoring Rules - Calibration Curves Advanced Topics - Out-of-distribution detection - Active learning for uncertainty reduction Applications of uncertainty estimation in machine learning

Module Components

Pflichtgruppe:

All Courses are mandatory.

Course Name	Type	Number	Cycle	Language	SWS	VZ
Uncertainty in Machine Learning	SEM		WiSe/SoSe	English	2

Workload and Credit Points

Uncertainty in Machine Learning (SEM):

Workload description	Multiplier	Hours	Total
Attendance	15.0	2.0h	30.0h
Pre/post processing	15.0	4.0h	60.0h
			90.0h(~3 LP)

The Workload of the module sums up to 90.0 Hours. Therefore the module contains 3 Credits.

Description of Teaching and Learning Methods

The module consists of a seminar. At the beginning of the semester, students will choose a topic based on a provided collection of published material. During the semester, students will become acquainted with the topic and prepare a presentation, where they regularly confer with their assigned advisor. At semester end, students will give a presentation as part of a block-seminar.

Requirements for participation and examination

Desirable prerequisites for participation in the courses:

A BSc degree in Computer Science is recommended. Successful completion of an introductory module on ML such as "Machine Learning I" or "Machine Intelligence I" is recommended. Basic knowledge of mathematics (particularly analysis, linear algebra and stochastics) is recommended.

Mandatory requirements for the module test application:

This module has no requirements.

Module completion

Grading

graded

Type of exam

Portfolio examination

Type of portfolio examination

100 Punkte pro Element

Language

English

Test elements

Name	Weight	Categorie	Duration/Extent
(Deliverable assessment) Online Quiz	50	written	45 min
(Deliverable assessment) Presentation	50	written	30 min

Grading scale

Notenschlüssel »Notenschlüssel 2: Fak IV (2)«

Gesamtpunktzahl	1.0	1.3	1.7	2.0	2.3	2.7	3.0	3.3	3.7	4.0
100.0pt	95.0pt	90.0pt	85.0pt	80.0pt	75.0pt	70.0pt	65.0pt	60.0pt	55.0pt	50.0pt

Test description (Module completion)

The module grade is calculated based on 1. The quality of a paper presentation (50%). 2. The performance in an online quiz comprising all presentations of the block-seminar (50%).

Duration of the Module

The following number of semesters is estimated for taking and completing the module:
1 Semester.

This module may be commenced in the following semesters:
Winter- und Sommersemester.

Maximum Number of Participants

The maximum capacity of students is 16.

Registration Procedures

Students can sign up for the course in MOSES.

Recommended literature
No recommended literature given

Assigned Degree Programs

Semester:

Zeige auch ausgelaufene Studiengänge und StuPOs

This module is used in the following Degree Programs (new System):

	Studiengang / StuPO	StuPOs	Verwendungen	Erste Verwendung	Letzte Verwendung
This module is not used in any degree program.

Miscellaneous

No information

Uncertainty in Machine Learning