de | en

Neural Engineering: Implants, Interfaces and Algorithms

Module EI7269

This Module is offered by TUM Department of Electrical and Computer Engineering.

This module handbook serves to describe contents, learning outcome, methods and examination type as well as linking to current dates for courses and module examination in the respective sections.

Module version of WS 2012/3

There are historic module descriptions of this module. A module description is valid until replaced by a newer one.

Whether the module’s courses are offered during a specific semester is listed in the section Courses, Learning and Teaching Methods and Literature below.

available module versions
SS 2017WS 2015/6WS 2012/3

Basic Information

EI7269 is a semester module in English language at Master’s level which is offered in summer semester.

This module description is valid from WS 2012/3 to WS 2018/9.

Total workloadContact hoursCredits (ECTS)
150 h 45 h 5 CP

Content, Learning Outcome and Preconditions

Content

Neuromorphic engineering is a new interdisciplinary research area that takes inspiration from biology, physics, mathematics, computer science, psychology and engineering to design artificial neural systems, such as autonomous robots, whose physical architecture and design principles are based on those of biological nervous systems. In this lecture students get introduced to computational principles of neuromorphic engineering, such as biological and artificial neural networks, distributed computation (e.g. believe propagation networks or agent based systems), event-based control (sensors and processing algorithms), analog VLSI chip design for neural inspired sensors and computing units, and neural vision processing algorithms for edge detection, optic flow computation or visual saliency.

Applications: design of (a) algorithms for sensory data processing and (b) autonomous cognitive systems to interact in real-time in real-world scenarios.

Learning Outcome

Nach dem Abschluss des Moduls sind Studierende in der Lage, grundlegende Konzepte des “Neural Engineering“ zu verstehen sowie die Anwendbarkeit einzelner Algorithmen im Bereich „Neuro-Prosthetik“ oder autonomer technischer Systeme zu bewerten.

Preconditions

recommended: lecture Computational Intelligence (or similar, such as introduction to Artificial Intelligence, machine learning).

No mandatory prerequisites.

Courses, Learning and Teaching Methods and Literature

Learning and Teaching Methods

Lectures will be held ex cathedra. In exercieses and tutorial courses, repeated calculations and problem solving will help develop deeper understanding for the matter.

Media

The following types of media are used:
- Presentations
- Lecture notes
- Tutorial exercises

Literature

Michael Arbib, The Handbook of Brain Theory and Neural Networks, MIT press

Module Exam

Description of exams and course work

Die verwendeten Teilprüfungen sind den verschiedenen Lernergebnissen angepasst:
A) Wissens- sowie verständnisbasierte Lernergebnisse sowie deren Transfer auf ähnlich gelagerte Probleme werden im Rahmen einer schriftlichen Klausur (90 min) überprüft, ggf. bei geringer Teilnehmerzahl auch durch eine mündliche Prüfung.
B) Die Fähigkeit zur individuellen Anwendung, Analyse und Bewertung der Vorlesungsinhalte wird im Rahmen einer Projektarbeit geprüft. Dabei setzen Teams von 2-3 Studierenden gegen Ende des Semesters ein selbst gewähltes Thema der Vorlesung in einem Demonstrator (Hardware oder Software) um; vergleichen ihr erstelltes System mit den Vorlesungsinhalten und berichten über Ihre Erfahrungen in einem kurzen Vortrag.

Die Endnote setzt sich wie folgt aus den Prüfungselementen zusammen:
A) Abschlussklausur: 70%
B) Projektarbeit gegen Ende des Semesters: 30%
Top of page