Delete search term


Quick navigation

Main navigation

CAI Colloquium

We invite AI experts to present and discuss topics relevant to the scope of the CAI. The colloquium takes place on Wednesdays from 11:00-12:00 at the Winterthur Campus of ZHAW.

Future Events

Date Time&Place Speaker Title Abstract
Wed, 23.11. 11:00-12:00, TS O1.19 and MS Teams Prof. Dr. Benjamin Grewe (ETHZ/UZH) Why auto-encoding is not enough In this talk, I will focus on the topic of how ‘human-like’ abstract representations can be learned in a self-supervised manner. To achieve this, we will take inspiration from neuroscience and animal/human learning and derive a new type of predictive learning scheme that is capable of learning disentangled representations. In this approach, an embodied agent is embedded in a learning environment in which it can act on a variety of objects to learn representations of these. At the end of the talk, I’ll introduce the abstraction-reasoning-corpus (ARC) challenge as a new benchmark to develop a new generation of interactive learning algorithms that mimic the ability and priors of humans solving the ARC challenge. I aim to conclude the talk with an open discussion on the general approach to self-supervised representation learning and how this relates to solving the ARC challenge.

Past Events

Date Speaker Title Slides
Wed, 19.10. Frank Wittmann & Meret Weiser (ZHAW) Algorithms and ML in Social Work
Wed, 20.7. 2nd Panel Discussion (Ch.v.d. Malsburg, R. Douglas, Y. Sandamirskaya, B. Grewe, T. Stadelmann, R. Chavarriaga) Pathways beyond present AI (Part 2): Artificial Intelligence: Game Over? News
Wed, 27.04. 1st Panel Discussion Pathways beyond present AI News
Wed, 30.3. Dr. Lucas Beyer (Google Brain) Transformers as general vision backbones
Wed, 2.3. Sebastian Welter (IKEA) Scaling AI in Enterprises PDF
Wed, 16.2. Prof. Dr. Volker Dellwo (UZH) Can speakers make themselves more recognisable?: Voice dynamics and its influence on voice recognition PDF
Wed, 17.11. Prof. Dr. Christoph von der Malsburg How can kids learn so much faster than transformers? Recording PDF
Wed, 8.9. Prof. Nicolaj Stache (HS Heilbronn) From Simulation to Reality using Reinforcement Learning PDF
Wed, 25.8. Prof. Marco Gori (U Siena) Learning to See by Motion Invariance PDF