Moses - Brain-Computer Interfacing

Display language

To modulepage Generate PDF

Module / Version:
#40362 / #8

Validity:
Seit WiSe 2022/23

Default display language:
English

Module title:
Brain-Computer Interfacing

Credits:
9

Responsible person:
Blankertz, Benjamin

Grading:
benotet

Type of exam:
Portfolioprüfung

Zugehörigkeit

Faculty:
Fakultät IV

Institute:
Institut für Softwaretechnik und Theoretische Informatik

Area of expertise:
34355200 FG S-Professur Neurotechnologie

Prüfungsausschuss:
No information

Kontakt

Office:
MAR 4-3

Contact person:
Miklody, Daniel

E-mail address:
benjamin.blankertz@tu-berlin.de

Website:

http://wiki.ml.tu-berlin.de/wiki/NT/Courses

Learning Outcomes

Students know the essential concepts of Brain-Computer Interfacing (BCI). They are capable of applying methods of biomedical signal processing and single-trial classification to neural data. They can provide an interpretation of the outcome of their analysis in a statistical as well as in a neurophysiological manner. Moreover, they are aware of potential issues imposed by machine learning applications, e.g., due to biases in the database. Through the seminar, they have more profound knowledge about special topics of BCI research in data analysis of physiological signals. Regarding methodology, independent of subject specific content, the students - are able to research sources and evaluate them reflectively - are able to present scientific topics in front of an audience and to discuss them critically - know presentation techniques in order to present the content of a lecture as clearly and comprehensibly as possible - have the ability to elaborate subject content in written form according to scientific standards - are able to manage their time sensibly

Content

IL: Approaches to Brain-Computer Interfacing (BCI); Event-related potentials (ERPs); Spatial filters; Multivariate analysis of brain signals; Single-trial classification of spatio-temporal features; Regularized discriminant analysis (RDA); The linear model (forward and backward) of EEG; Interpretation of spatial patterns and filters; Modulation of spontaneous brain rhythms; Event-related synchronization and desynchronization (ERS, ERD); Common spatial pattern (CSP) Analysis; Classification of spatio-spectral features; Signal decomposistion methods; Supervised and unsupervised methods of adaptation in the classification of EEG; Experimental design SE: Literature search, presentation techniques; Examplary topics: Neural correlates of attention in free viewing, Predictors of BCI Performance, Co-adaptive Systems, Control by Spatial Attention; Hybrid BCIs, Multimodal BCIs

Module Components

Pflichtteil:

All Courses are mandatory.

Course Name	Type	Number	Cycle	Language	SWS	VZ
Brain-Computer Interfacing	IV	3435 L 501	WiSe	No information	4
Current Topics in Brain-Computer Interfacing	SEM	3435 L 502	WiSe	No information	2

Workload and Credit Points

Brain-Computer Interfacing (IV):

Workload description	Multiplier	Hours	Total
Attendance	15.0	4.0h	60.0h
Pre-/post-processing	15.0	2.0h	30.0h
Preparing for written tests	2.0	15.0h	30.0h
Solving assignments	10.0	6.0h	60.0h
			180.0h(~6 LP)

Current Topics in Brain-Computer Interfacing (SEM):

Workload description	Multiplier	Hours	Total
Attendance, presentations, discussions	10.0	1.5h	15.0h
Pre/post-processing	1.0	75.0h	75.0h
			90.0h(~3 LP)

The Workload of the module sums up to 270.0 Hours. Therefore the module contains 9 Credits.

Description of Teaching and Learning Methods

The integrated lecture (IL) consists of a lecture (mainly teacher-centered, with some period of group work) and assignments. The latter require independently solving programming exercises and working on complex tasks under guidance of a tutor. After an introduction to literature research, participants choose topics and presentation formats, e.g. talk, wiki articles, screencast video. For an early overview of the topic, each participant gives a one-minute presentation. After further familiarization with the topic, spotlight presentations (about 5 minutes) are given. Upon completion of the main presentation, participants will write comments on selected presentations by their peers. Seminar presentations are developed under the guidance of a supervisor.

Requirements for participation and examination

Desirable prerequisites for participation in the courses:

* Mandatory: programming skills in python; background in mathematics, in particular linear algebra and probability theory. * Helpful, but not obligatory: Basic knowledge in signal processing and machine learning.

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: 10 Assignments	15	practical	6h each
Examination: 2 written tests	60	written	jeweils 60 min
Deliverable assessment: Presentations in the seminar	25	flexible	30 min or 8 pages

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 grade is determined according to § 47 (2) AllgStuPO with the grading system 2 of faculty IV. * Exercises: Concurrent to the lecture, there will be a tutorial in which ten assignment sheets have to be solved. These are devoted to practical EEG analysis (programming). * Written exams: In the first half and in the second half of the lecture, there will be a written test of about 60 minutes. * Seminar presentation: Presentation of a research topic (various formats: orally with slides or written report or wiki articles or screencast video; options may differ from year to year);moreover: short presentations, contributions to discussion, commentaries

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:
Wintersemester.

Maximum Number of Participants

The maximum capacity of students is 25.

Registration Procedures

Registration is not required, but stating the interest to participate in the lecture is welcome for the planning of resources. * Either email to Sekr. MAR 4-3: Imke Weitkamp <imke.weitkamp@tu-berlin.de> * or register in the respective courses in the information system at https://isis.tu-berlin.de/

Recommended literature
Blankertz B, Lemm S, Treder MS, Haufe S, Müller KR, Single-trial analysis and classification of ERP components - a tutorial, Neuroimage, 56:814-825, 2011.
Blankertz B, Tomioka R, Lemm S, Kawanabe M, Müller KR, Optimizing Spatial Filters for Robust EEG Single-Trial Analysis, IEEE Signal Process Mag, 25(1):41-56, 2008.
Dornhege G, R. Millán J d, Hinterberger T, McFarland D, Müller K (eds), Toward Brain-Computer Interfacing, MIT Press, 2007.
Parra LC, Spence CD, Gerson AD, Sajda P. Recipes for the Linear Analysis of EEG, Neuroimage, 28(2):326-341, 2005.

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	4	WiSe 2022/23	SoSe 2024
Computer Engineering (M. Sc.)	1	16	WiSe 2022/23	SoSe 2024
Computer Science (Informatik) (M. Sc.)	1	8	WiSe 2022/23	SoSe 2024
Elektrotechnik (M. Sc.)	1	12	WiSe 2022/23	SoSe 2024
Wirtschaftsingenieurwesen (M. Sc.)	1	8	WiSe 2022/23	SoSe 2024

Miscellaneous

No information

Brain-Computer Interfacing