Institute
General information about the institute, such as our mission statement, organizational structure, staff directory, history, directions, etc.

See More
Research
Scientific profile with all research groups, topics, collaborations, as well as columns on research at the institute.

See More
News
News and press releases about the institute, as well as a media archive.

See More
- News Overview
- Press Releases
Events
Overview of all events around the institute, such as talks, seminars, lectures, workshops, conferences and public events.

See More
Publications
Overview of all scientific publications of the institute, as well as our preprint and software repositories.

See More
Career
Information on open positions at the institute, benefits of working with us, graduate school, and postdoctoral supervision.

See More

Events
Mathematical Methods in Data Science

MPI for Mathematics in the Sciences

G3 10 (Lecture hall)

seminar

24.05.24 12.07.24

Mathematical Methods in Data Science

Upcoming Events of this Seminar

talk

24.05.24, 09:00

What are graph neural networks?

Celia Hacker (MPI MiS, Leipzig)

See Details

talk

31.05.24, 09:00

The Geometry of Kernel Methods and Kernel Range Spaces

Jeff Philips (MPI MiS, Leipzig)

See Details

talk

07.06.24, 09:00

to be announced

Simon Telen (MPI MiS)

See Details

talk

14.06.24, 09:00

to be announced

Parvaneh Joharinad (ScaDS.AI, Leipzig University + MPI MiS, Leipzig)

See Details

talk

21.06.24, 09:00

Topology-Preserving Data Compression

Bei Wang Phillips (University of Utah + MPI MiS, Leipzig)

See Details

talk

05.07.24, 09:00

to be announced

Marzieh Eidi (ScaDS.AI, Leipzig University + MPI MiS, Leipzig)

See Details

talk

12.07.24, 09:00

to be announced

Karel Devriendt (MPI MiS, Leipzig)

See Details

Previous Events


10.05.24	Justin Curry (University of Albany, USA) To Predict is NOT to Explain Modern day neural networks are amazing prediction machines, but to get at explanations one has to understand higher order relations between data as they fiber over their predictions. In this talk I will connect the urgent questions of modern data science with the distinguished history of applied topology by considering simple geometric examples and probing them with increasingly complicated tools. Ideas from dynamics, stratification theory and sheaf theory will be introduced in a loose and intuitive fashion to trace future directions for research.

10.05.24

Justin Curry (University of Albany, USA)

To Predict is NOT to Explain

Modern day neural networks are amazing prediction machines, but to get at explanations one has to understand higher order relations between data as they fiber over their predictions. In this talk I will connect the urgent questions of modern data science with the distinguished history of applied topology by considering simple geometric examples and probing them with increasingly complicated tools. Ideas from dynamics, stratification theory and sheaf theory will be introduced in a loose and intuitive fashion to trace future directions for research.

Mathematical Methods in Data Science

Upcoming Events of this Seminar

What are graph neural networks?

The Geometry of Kernel Methods and Kernel Range Spaces

to be announced

to be announced

Topology-Preserving Data Compression

to be announced

to be announced

Previous Events

Scientific Organizers

Diaaeldin Taha

Administrative Contact

Antje Vandenberg