Moses - Machine Learning 1-X

Display language

To modulepage Generate PDF

Module / Version:
#40834 / #4

Validity:
Seit SoSe 2020

Default display language:
English

Module title:
Machine Learning 1-X

Credits:
12

Responsible person:
Müller, Klaus-Robert

Grading:
benotet

Type of exam:
Schriftliche Prüfung

Zugehörigkeit

Faculty:
Fakultät IV

Institute:
Institut für Softwaretechnik und Theoretische Informatik

Area of expertise:
34352000 FG Maschinelles Lernen

Prüfungsausschuss:
No information

Kontakt

Office:
MAR 4-1

Contact person:
Montavon, Gregoire

E-mail address:
klaus-robert.mueller@tu-berlin.de

Website:

https://wiki.ml.tu-berlin.de/wiki/

Learning Outcomes

The students are able to independently apply methods from machine learning on new data. This includes methods for classification, regression, dimensionality reduction and clustering. Moreover, the module teaches the mathematical skills (probability theory, optimization theory) needed to extend and theoretical analyze machine learning methods.

Content

Probability theory, theory of estimation (e.g. Maximum likelihood, EM algorithm) Methods from Machine Learning: Dimensionality reduction (PCA), Clustering, Supervised learning (e.g. Regression, LDA, SVM, Gaussian processes) Depending on the elective: more detailed knowledge about specific machine learning problems, programming skills, or mathematical foundations.

Module Components

Pflichtgruppe:

All Courses are mandatory.

Course Name	Type	Number	Cycle	Language	SWS	VZ
Maschinelles Lernen I	IV	0434 L 501	WiSe	English	6

Wahlpflicht:

Please choose courses with 3 credit(s) from the following courses.

Course Name	Type	Number	Cycle	Language	SWS
Algorithms for brain reading and writing	SEM		WiSe	No information	2
Bayesian Learning	VL	343 L 8043	WiSe	No information	2
Big Data: Skalierbares Maschinelles Lernen	KU		WiSe	No information	2
Big Data: Skalierbares Maschinelles Lernen	SEM		WiSe	No information	2
Boosting and Model Averaging	SEM		WiSe/SoSe	No information	2
Classical Topics in ML	SEM	0434 L 588	WiSe	No information	2
Deep Neural Networks	VL		WiSe/SoSe	No information	2
Machine Learning and Data Management Systems	SEM		WiSe/SoSe	No information	2
Machine Learning in the Sciences	VL		SoSe	No information	2
Mathematische Grundlagen für Maschinelles Lernen	KU	0434 L 545	WiSe/SoSe	No information	2
Matlabprogrammierung für ML und Datenanlyse	KU	0434 L 544	WiSe/SoSe	No information	2
Pythonprogrammierung für ML und Datenanalyse	KU	0434 L 543	WiSe/SoSe	English	2
Scientific applications in Machine Learning	SEM		WiSe/SoSe	No information	2

Workload and Credit Points

Maschinelles Lernen I (IV):

Workload description	Multiplier	Hours	Total
			270.0h(~9 LP)
Concepts & Theory	15.0	6.0h	90.0h
Exercises	15.0	6.0h	90.0h
Programming	15.0	6.0h	90.0h

Algorithms for brain reading and writing (SEM):

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

Bayesian Learning (VL):

Workload description	Multiplier	Hours	Total
			90.0h(~3 LP)
No information	15.0	2.0h	30.0h
No information	15.0	4.0h	60.0h

Big Data: Skalierbares Maschinelles Lernen (KU):

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

Big Data: Skalierbares Maschinelles Lernen (SEM):

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

Boosting and Model Averaging (SEM):

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

Classical Topics in ML (SEM):

Workload description	Multiplier	Hours	Total
			90.0h(~3 LP)
No information	15.0	2.0h	30.0h
No information	15.0	4.0h	60.0h

Deep Neural Networks (VL):

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

Machine Learning and Data Management Systems (SEM):

Workload description	Multiplier	Hours	Total
			90.0h(~3 LP)
No information	15.0	4.0h	60.0h
No information	15.0	2.0h	30.0h

Machine Learning in the Sciences (VL):

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

Mathematische Grundlagen für Maschinelles Lernen (KU):

Workload description	Multiplier	Hours	Total
			90.0h(~3 LP)
No information	15.0	2.0h	30.0h
No information	15.0	4.0h	60.0h

Matlabprogrammierung für ML und Datenanlyse (KU):

Workload description	Multiplier	Hours	Total
			90.0h(~3 LP)
No information	15.0	2.0h	30.0h
No information	15.0	4.0h	60.0h

Pythonprogrammierung für ML und Datenanalyse (KU):

Workload description	Multiplier	Hours	Total
			90.0h(~3 LP)
No information	15.0	2.0h	30.0h
No information	15.0	4.0h	60.0h

Scientific applications in Machine Learning (SEM):

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

The Workload of the module sums up to 360.0 Hours. Therefore the module contains 12 Credits.

Description of Teaching and Learning Methods

weekly lectures, tutorials, and homeworks

Requirements for participation and examination

Desirable prerequisites for participation in the courses:

Basic knowledge in linear algebra and calculus. Basic knowledge in probability theory. Basic programming knowledge, programming in Python.

Mandatory requirements for the module test application:

1. Requirement

Machine Learning 1-X: Übungsschein Wahlpflichtveranstaltung bestanden

Module completion

Grading

graded

Type of exam

Written exam

Language

English

Duration/Extent

120 min

Duration of the Module

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

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

Maximum Number of Participants

This module is not limited to a number of students.

Registration Procedures

cf. course webpage

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
Biomedizinische Technik (M. Sc.)	1	9	SoSe 2021	SoSe 2023
Computational Engineering Science (Informationstechnik im Maschinenwesen) (M. Sc.)	1	5	SoSe 2022	SoSe 2023
Computer Engineering (M. Sc.)	1	42	SoSe 2020	SoSe 2023
Computer Science (Informatik) (M. Sc.)	1	35	SoSe 2020	SoSe 2023
Elektrotechnik (M. Sc.)	1	21	SoSe 2020	SoSe 2023
ICT Innovation (M. Sc.)	2	7	SoSe 2020	SoSe 2023
Information Systems Management (Wirtschaftsinformatik) (M. Sc.)	2	13	SoSe 2020	SoSe 2023
Physikalische Ingenieurwissenschaft (M. Sc.)	2	8	WiSe 2021/22	SoSe 2023
Wirtschaftsingenieurwesen (M. Sc.)	1	18	SoSe 2020	SoSe 2023

Students of other degrees can participate in this module without capacity testing.

Miscellaneous

No information

Machine Learning 1-X