Advanced Brain-Computer Interfacing
Course infoSchedule
Course moduleSOW-MKI74
Credits (ECTS)6
CategoryMA (Master)
Language of instructionEnglish
Offered byRadboud University; Faculty of Social Sciences; Artificial Intelligence;
PreviousNext 1
dr. M.W. Tangermann
Other course modules lecturer
dr. M.W. Tangermann
Other course modules lecturer
Contactperson for the course
dr. M.W. Tangermann
Other course modules lecturer
dr. M.W. Tangermann
Other course modules lecturer
dr. J. Thielen
Other course modules lecturer
Academic year2023
SEM2  (29/01/2024 to 12/07/2024)
Starting block
Course mode
Registration using OSIRISYes
Course open to students from other facultiesYes
Waiting listNo
Placement procedure-
Upon successful completion of the course, the student can:
  • describe hardware developments for signal recording (e.g., dry EEG electrodes, optically pumped magnetoencephalography, ECoG);
  • understand and compare advanced experimental protocols such as improved and real-time adaptive stimulus protocols and relate this to the neuroscientific background;
  • understand and compare advanced algorithms used in the BCI field for data preprocessing, feature extraction and decoding, for instance which are capable to deal with domain-specific challenges such as extremely small datasets, zero-training approaches, non-stationary feature distributions, low signal-to-noise, transfer learning, domain-specific regularization, end-to-end learning, etc.;
  • describe several applications of BCI technology other than communication and control such as neurorehabilitation and neurofeedback;
  • apply the aforementioned theory and implement state-of-the-art BCI pipelines;
  • critically reflect on state-of-the-art scientific publications and write a project proposal.
The Advanced Brain-Computer Interfacing (BCI) course goes beyond the Bachelor level BCI course with respect to multiple aspects. It comprises 
  • advanced experimental protocols beyond the widely used standard visual evoked potential paradigms and motor imagery tasks
  • novel algorithms for the decoding of brain signals using e.g. convolutional neural networks or Riemannian geometry, and decoding approaches which address specific shortcomings of standard BCI data analysis pipelines, e.g. when extremely small data sets have to be dealt with or for non-stationary data, or when labeled training data can not be obtained.
  • special applications beyond text spelling and control, e.g. BCI-supported rehabilitation
Presumed foreknowledge
We assume that the student possesses: 
  • sound mathematical background, specifically on linear algebra, and probability theory;
  • an understanding of how a brain-computer interface (BCI) works and its limitations;
  • an understanding of basic experimental protocols, specifically imagery tasks that modulate oscillatory EEG activity and stimulation protocols resulting in event-related potentials of the EEG
  • an understanding of how these protocols can be transformed into practical BCI systems and applications for communication and control;
  • a thorough understanding of algorithms for basic signal (pre-)processing, feature extraction (e.g. data-driven spatial filters), classification and regression models which allow to decode these brain signals on a single-trial level;
  • Python programming skills to implement and evaluate these algorithms in an offline analysis;
  • the ability to work with a state-of-the-art library for the training and evaluation of deep neural networks

Strongly advised knowledge of the following or equivalent courses
  • Linear Algebra (SOW-BKI124), or equivalent courses;
  • Probability Theory (SOW-BKI137), or equivalent courses;
  • Signal Processing (SOW-BKI323), or equivalent courses;
  • At least one course on machine learning, e.g., Deep Learning (SOW-BKI230A) or Data Mining (NWI-IBI008), or equivalent courses.
Test information
Type of test (exam; essay; (group/individual) assignment(s) etc.:
  1. a written essay in the form of e.g. a project proposal or a comparison of two papers (to be determined) has to be passed.
  2. a written, graded closed-book exam at the end of the course.
Possibility to resit of each type;
  1. The written essay cannot be resit.
  2. The written exam can be resit.
Weight of each type:
  1. Passing the written essay is necessary to be allowed to participate in the written exam.
  2. The written exam defines 100% of the course grade.
Minimum grade of each type:
  1. Essay: pass (only pass or fail)
  2. Written exam: at least 5.5
The grade (pass/fail) for the essay will be communicated in Brightspace. Only the final grade will appear in Osiris.
Please sign up for any course at (, it is obligatory.

Students who are enrolled for a course are also provisionally registered for the exam. 

Resit: Manual register at ( until five working days prior to the date of the exam. No delayed registration is possible. 

We urge you to always read the course information on Brightspace. 

Required materials
Reading materials are announced on a topic-by-topic basis.

Instructional modes
Lab sessions
Attendance MandatoryYes

Lab sessions (attendance compulsory -- only if the corona situation and lab status allows)


Probably mixture of online and on-campus

Work groups

Work group (attendance is not compulsory), probably mixture of online and on-campus

Test weight1
Test typeExam
OpportunitiesBlock SEM2, Block SEM2