Tech Events in Heidelberg

How can we uncover the most meaningful factors hidden in complex data and understand what each of them actually represents?

We are happy to welcome Prof. Dr. Ullrich Köthe from Heidelberg University to heidelberg.ai to talk about EOFlows, a non-linear extension of Principal Component Analysis (PCA).
PCA identifies the main factors of variation in a dataset, but it is limited to linear relationships. Normalizing flows can capture more complex patterns, but they lack interpretability.
EOFlows aim to combine the flexibility of normalizing flows with the interpretability of PCA. Using orthogonality regularization, they learn latent dimensions that capture distinct factors of variation, which can be ranked by their explained entropy.
In this talk, Prof. Köthe will explain how EOFlows work and show what they discover in the CelebA portrait dataset. He will also discuss how stable the results are across training runs and how the method compares with existing approaches.

About Ullrich Köthe
Ullrich Köthe is an Associate Professor at Heidelberg University, where he has led a group in the Visual Learning Lab since 2018. His research spans image analysis, machine learning, and explainable AI, with a focus on developing methods that make the inner workings of neural networks easier to understand.

For more info go to: https://www.heidelberg.ai/2026/11/10/ullrich-koethe.html

After the event, we will also upload a video recording to our YouTube channel: https://www.youtube.com/channel/UCfHWBneOsb7SfOxJepnMQKA

Der Workshop besteht aus zwei Terminen, in denen du dir deine eigene Tasche passgenau für dein Fahrrad selber nähen kannst! Mit der vielfältigen Farbauswahl kannst du deine Tasche auch farblich auf dein Fahrrad abstimmen oder ein halt ein richtiges Statement-Piece machen 🍭

Wann? 10. und 26. November um 17 Uhr
Wo? Im Gemeinschaftsraum des CoMakingSpace

Anmeldung & Details unter:
https://pretix.eu/comakingspace/radtaschen-112026/

Wir freuen uns auf eure kreativen Ideen!

Whatever you want to make, we try to make it possible together! Come check out the CoMakingSpace :-)

During this weekly meetup, volunteers offer guidance and supervision for members as well as tours for those who are interested in our community workshop! Besides Raspberry Pi and other electronics projects, you could try your hand at woodworking, metalworking, 3D printing, CNC routing or laser cutting, for example.
Machine introductions are not always possible on short notice, especially when it's a busy evening - best arrange yourself with a tutor in advance!

• Wichtig zu wissen
membership options to work on your own projects // Mitgliedschaft um selbst zu werkeln

Join us on Thursday 3 December for a festive deep-dive into how knowledge graphs and semantic layers create the context layer that AI needs to be trustworthy.

LLMs have come a long way, but without context they still guess. Whether you want to mitigate hallucinations, govern your enterprise data model at scape, or build secure agents that understand your business, this evening serves up practical insights alongside some seasonal cheer.

What we’ll explore

• How knowledge graphs ground LLM answers in verifiable business knowledge
• Where a semantic layer fits between your data sources and your AI
• What it takes to build context-aware agents that work securely in production
• Lessons from open knowledge projects and from regulated, data-heavy industries

After the talks, we’ll head over to the Christmas market in Heidelberg. If you’d like to join us for a drink and more conversation, you’re very welcome. No need to sign up separately.

Our speakers

• Denny Vrandečić, co-creator of Wikidata: "Beyond Graphs: Knowledge Representation in the Age of LLMs"
• Andrea Splendiani, IQVIA
• Sebastian Schmidt, Digital Science

Who should come
Data and knowledge engineers, architects, AI/ML practitioners, ontologists, and product and data leaders who want to move from AI experiments to AI they can trust. Newcomers are welcome. You don’t need to be a graph expert to follow along.

Open Source conference in Heidelberg, Germany

Python conference in Heidelberg, Germany