Foundations of data science

This course is listed in Aachen RWTHonline as Foundations of data science, in Bonn Basis as MA-INF 4228 Foundations of data science.

Data science aims at making sense of big data. To that end various tools have to be understood for helping in analyzing the arising structures.

Often data comes as a collection of vectors with a large number of components. To understand their common structure is the first main objective of understanding the data. The geometry and the linear algebra behind them become relevant and enlightening. Yet, the intuition from low-dimensional space turns out to be often misleading. We need to be aware of the particular properties of high-dimensional spaces when working with such data. Fruitful methods for the analysis include singular vector decomposition from linear algebra and supervised and unsupervised machine learning. If time permits we also consider random graphs which are the second most used model for real world phenomena.

Michael Nüsken

• Monday, 12¹⁵ c.t.-14⁰⁰, BigBlueButton/moodle lecture room [b-it bitmax (0.109)].
• Thursday, 12⁰⁰ c.t.-14⁰⁰, BigBlueButton/moodle lecture room [b-it bitmax (0.109)].
• Tutorial: Monday, 14⁰⁰ c.t.-16⁰⁰, BigBlueButton/moodle tutorial room [b-it bitmax (0.109)].

First meeting: Monday, 20 April 2020, 12¹⁵-16⁰⁰ with a break. This is a double session!
You must be enrolled in the moodle to enter the lecture room.

Pre-exam meeting: Thursday, 13 August 2020, 10⁰⁰-12⁰⁰, BigBlueButton/moodle lecture room.

Exam: Monday, 17 August 2020, 10⁰⁰-13⁰⁰, room Wolfgang-Paul-Hörsaal, Kreuzbergweg 28, 53115 Bonn.

Post-exam meeting: individual exam reviews.

Exam2: Thursday, 24 September 2020, 13⁰⁰-15⁰⁰, Meckenheimer Allee 176, Hörsäle 2 und 4.

Post-exam2: individual exam reviews,

You will find notes and exercises at sciebo until March 2021.

• Avrim Blum, John Hopcroft, and Ravindran Kannan (2020). Foundations of Data Science. Cambridge University Press, ISBN 9781108485067, eISBN 9781108620321.
  Drafts are on Hopcroft's page: PDF.
• Olivier Bousquet, Stéphane Boucheron & Gábor Lugosi (2004). Introduction to Statistical Learning Theory. In Bousquet, v. Luxburg & G. Rätsch (editors), Advanced Lectures in Machine Learning, Springer, pp. 169--207, 2004. Webpage, PDF.
• Marc Peter Deisenroth, A Aldo Faisal, and Cheng Soon Ong (2019). Mathematics for Machine Learning. Webpage with PDF.

4+2 SWS.

• Master in Media Informatics:
  8 ECTS credits.
  Students have to register this course with RWTHonline.
• Master in Computer Science at University of Bonn: MA-INF 4228.
  9 CP.
  Students have to register for the exam to this course with POS/BASIS (see here).

Students are encouraged to ask and answer any questions related to the course on the mailing list:

20ss-fds-at-lists.bit.uni-bonn.de

You can subscribe to and unsubscribe from the mailing list using the information given on the list's Info page.