| NUMMER: | 212014 |
| KÜRZEL: | IntroNDS |
| MODULBEAUFTRAGTE:R: | Prof. Dr. Robert Schmidt |
| DOZENT:IN: | Prof. Dr. Robert Schmidt M.Sc. Gergö Gömöri |
| FAKULTÄT: | Fakultät für Informatik |
| SPRACHE: | Englisch |
| SWS: | 4 |
| CREDITS: | 5 |
| ANGEBOTEN IM: | jedes Wintersemester |
LINK ZUM VORLESUNGSVERZEICHNIS
Hier entlang.
LERNFORM
In the lectures different topics of neural data science will be introduced and discussed. This
will then be complemented by practical computer exercises, in which students will gain hands-
on experience on methods in neural data science.
LERNZIELE
* Know what signals can be measured from brain activity and how they are processed using data science methods* Be aware of challenges in neuroscience data sets and how they can be addressed using machine learning methods
* Apply data analysis methods to neural data and visualize and interpret the results
INHALT
Rapid technological advances have recently opened up new possibilities in understanding howthe brain works. In particular the number of neurons that can be simultaneously recorded has
increased considerably to hundreds (and soon thousands!) of neurons. However, this has lead
to a big challenge on how to actually process and analyze the resulting big data sets. Solutions
for these challenges are part of the new exciting research field of 'Neural Data Science'. In this
module you will learn how methods and approaches from data science and machine learning
can be applied to study brain signals and the related cognitive functions. In the first part of the
module we will focus on so-called spike trains, how they can be analyzed, visualized, and
decoded. In the second part of the module we will look at continuous signals, in particular at
neural oscillations. Finally, we will learn about and apply some advanced methods from
machine learning, such as dimensionality reduction approaches, reinforcement learning,
clustering, and computational statistics. In the lectures I will provide the relevant neurobiological background and explain the computational approaches, which will then be
applied in the computer exercises using real neural data sets.
VORAUSSETZUNGEN CREDITS
Passed written exam
EMPFOHLENE VORKENNTNISSE
Basic knowledge of calculus and linear algebra, programming in Python