See TUMonline
Note: MSNE

After the practical course students are able to: - understand the concept of neuro-inspired systems engineering, are familiar with related terminology, exemplary state-of-the art work, and chances and challenges related to the topic (A). - implement functional modules of neuro-inspired systems/algorithms in form of programming exercises (A). - work independently on a practical project related to neuro-inspired systems with regular colloquia with an assigned supervisor (B1); preparing and summarizing the results in an elaborate written report (B2). - present and defend the project in front of a committee of scientific and technical experts (B3).

This module provides an introduction to the concept of neuro-inspired systems engineering. The first part of the course comprises an extensive illustration of mainly TUM-based state-of-the-art research that makes use of interdisciplinary approaches in systems engineering, linking e.g. to neuro-biology or cognitive sciences. This is to give the students both an overview of current works in the field of Neuroengineering and help them decide on the topic of their final thesis. The second part of the course will illustrate and build up on state-of-the-art definitions, terminologies, standardizations, as well as theoretical and practical chances and challenges in the field of neuro-inspired systems engineering.

Programming skills in Matlab required, some background in C/C++, Python is recommended. Basic knowledge in statistical signal processing and machine learning is recommended.

The theoretical lectures will introduce the students into the concept and foundations of selected topics of neuro-inspired systems engineering. Three thematic blocks: EEG based brain-state decoding and brain-computer interfaces; visual attention and predictive coding for robotic systems; and artificial robotic skin and neuromorphic event-based processing (A1). The theoretical lectures are accompanied by supervised tutorials and programming exercises. These serve to consolidate the theoretical content of the lectures in a practical fashion (A2) and likewise prepare the students for the independent project work. The independent project work allows the students to practically use the knowledge and skills aquired in A. Experienced supervisors (B1) provide guidance from the initiation of the project idea until its finalization. The project work is to be presented and defended in form of a written report (B2) and an oral presentation in front of a professional audience (B3). Both items B2 and B3 provide the students practical experience in presenting their own research work in a scientifically sound fashion.

The student's individual coursework is validated with a practical project and consists of the following items: (A) Homework (first half of the semester): 3-5 individual homeworks for consolidation of theoretical content given in the lectures. The homeworks also serve as a preparation for the project work and are evaluated regarding completeness, quality and originality. (B) Independent practical project (second half of the semester): (B1) Regular colloquia with assigned supervisor on working progress for assessing the student's capability of organizing the project and to provide guidance. (B2) Written report (10-15 pages), serving to prove that the students have properly understood the linkage between the theoretical background and the practical realization. (B3) Oral presentation (5-10 min) of the results with following oral colloquium (2-5 min). This serves to prove the student is able to defend her work in front of a committee of scientific and technical experts.

Cheng, G. (2014). Humanoid robotics and neuroscience: Science, engineering and society. CRC Press. DOI: 10.1201/b17949-3 Wolpaw, J., & Wolpaw, E. W. (Eds.). (2012). Brain-computer interfaces: principles and practice. OUP USA. Rao, R. P. (2013). Brain-computer interfacing: an introduction. Cambridge University Press. Corbetta, M., & Shulman, G. L. (2002). Control of goal-directed and stimulus-driven attention in the brain. Nature reviews neuroscience, 3(3), 201. Itti, L., & Koch, C. (2000). A saliency-based search mechanism for overt and covert shifts of visual attention. Vision research, 40(10-12), 1489-1506. Dahiya, R. S. & Valle, M. Dahiya, R. S. & Valle, M. (Eds.) Robotic Tactile Sensing: Technologies and System Springer, 2013 Kandel, E. R.; Schwartz, J. H.; Jassell, T. M.; Siegelbaum, S. A. & Hudspeth, A. J. Kandel, E. R.; Schwartz, J. H.; Jassell, T. M.; Siegelbaum, S. A. & Hudspeth, A. J. (Eds.) Principles of Neural Science, Fifth Edition The MacGraw-Hill Companies, 2013