Talks, workshops, and more
This page contains some of my talks, presentations, and links to other things I am organising, such as machine learning outreach programmes. Feel free to use any illustrations from the slides—as long as you attribute me as the original creator. If you want to get the original sources of the graphics, just reach out to me.
Check out my YouTube channel for more content!
Contents
Talks

A Bestiary of Autoencoders
March 2021; slides for the Digital Campus of DBSSE. 
Topological Representation Learning for Structured and Unstructured Data
February 2021; slides for an invited talk at the DataShape seminar of Inria Sophia Antipolis.
This PDF is best viewed with a PDF viewer that supports animations, such as Adobe Acrobat Reader DC 
Recent Advances in TopologyBased Graph Classification
December 2020; slides for an invited talk in the Applied Mathematics Seminar of Yale University. This is similar to the talk I gave in October, but there are some pointers towards more recent work of TDA in a metric space setting. 
A Primer in Topological Data Analysis (Lecture 1, Lecture 2)
November 2020; slides for a guest lecture in the course Geometric Data Analysis of Prof. Guy Wolf at Université de Montréal.
The second lecture PDF is best viewed with a PDF viewer that supports animations, such as Adobe Acrobat Reader DC 
Advances in TopologyBased Graph Classification
October 2020; slides for an invited talk at the University of Oxford Data Science Seminar and at Michael Bronstein’s research group at Twitter. 
TopologyBased Representation Learning
July 2020; slides for an invited talk at the research group of Prof. Kathryn Hess Bellwald at EPFL
This PDF is best viewed with a PDF viewer that supports animations, such as Adobe Acrobat Reader DC 
The Many Faces of Manifolds
February 2020; slides for the intradepartmental seminar at DBSSE in Basel 
Introduction to TopologyBased Graph Classification
January 2020; slides for an invited talk at the AI & Topology session of the Applied Machine Learning Days in Lausanne 
Perspectives in Persistent Homology
September 2019; slides for a keynote talk at the Applications of Topological Data Analysis Workshop colocated with ECMLPKDD 2019 in Würzburg 
Introduction to Machine Learning for Biology
June 2019; workshop slides for the 2019 DBSSE Retreat in Muttenz 
An Enchiridion for Topological Data Analysis
June 2018; talk at Basel Postdoc Retreat in Klosters 
Statistically significant shapelet mining for biomedical time series
June 2018; invited talk in the graduate seminar of Prof. Filip Sadlo 
Shakespearean Social Network Analysis using Topological Methods
July 2016; lecture in the graduate seminar of Prof. Filip Sadlo 
An introduction to persistent homology
May 2016; public lecture for the SIAM Chapter Heidelberg 
Ein Bild sagt mehr als tausend Worte: Graphische Darstellungen komplexer Daten
May 2016; public lecture for the ‘Akademische Mittagspause 2016’ lecture series 
Persistent homology for multivariate data visualization
Februrary 2016; invited talk at Sorbonne Universités UPMC in the research group by Dr. Julien Tierny 
Aspects of human perception
June 2015; lecture in a course of Dr. Hubert Mara 
Die PoincaréVermutung
May 2014; lecture in a course at ‘Privatgymnasium St. LeonRot’, a private high school 
Aspekte menschlicher Wahrnehmung
January 2014; lecture in a course of Dr. Hubert Mara 
Weniger Klartext reden!
September 2013; public lecture for the ‘Science Academy’ 
Oh my god, it’s full of data–A biased & incomplete introduction to visualization
April 2013; lecture in the fellows seminar of my graduate school 
Die PoincaréVermutung
September 2012; public lecture for the ‘Science Academy’ 
Applied algebraic topology
July 2011; informal presentation I gave as a precursor to my Ph.D. project
Tutorials
 ‘Topological Data Analysis for Machine Learning’ at ECML PKDD 2020
Topological Machine Learning is a nascent domain of machine learning research that employ concepts from (applied) topology to improve or analyse machine learning models. I gave a fourpart tutorial on this topic for a general computer science audience that was not necessarily exposed to the mathematical background.