Thursday Morning Talk

Hector Garcia de Marina (University of Granada), “Practical challenges in formation control and mobile robot swarms”

MAR 2.057

Abstract: Robot swarms have the potential to assist us with simpler logistics in persistent missions involving vast scenarios. Robot swarms also promise added resilience to complete their objectives despite unforeseen difficulties. However, current demonstrations of swarm technology in unstructured environments only count on single-digit individuals. That is farther from what one would expect from the

Thursday Morning Talk

Pavel Němec (Charles University), “Two independent origins of complex brains and intelligent behavior in birds and mammals”

Abstract: Over the last 20 years, it has been shown that birds and mammals are startlingly similar in their cognitive repertoire. Even the most intelligent taxa from each group – great apes and large corvids and parrots – match each other in most domains of cognition. This functional similarity is remarkable considering that birds and

Distinguished Speaker Series

Serge Belongie (University of Copenhagen), “Searching for Structure in Unfalsifiable Claims”

Abstract: While advances in automated fact-checking are critical in the fight against the spread of misinformation in social media, we argue that more attention is needed in the domain of unfalsifiable claims. In this talk, we outline some promising directions for identifying the prevailing narratives in shared content (image & text) and explore how the

For the Public

Girls’ Day 2024

This year, SCIoI is once again delighted to be part of Girls' Day, an event dedicated to offering school-aged girls the opportunity to explore new experiences and gain insights into the realm of STEM related research. This time around, our researchers Palina Bartashevich, Asieh Daneshi, Soledad Traverso, Anna Lange, and David Mezey, with the help

Thursday Morning Talk

Joshua B. Evans, “Creating Multi-Level Skill Hierarchies in Reinforcement Learning”

Abstract: What is a useful skill hierarchy for an autonomous agent? In this talk, we will consider a possible answer based on a graphical representation of how the interaction between an agent and its environment may unfold. The proposed approach uses modularity maximisation as a central organising principle to expose the structure of the interaction

Thursday Morning Talk

Verena Wagner (University of Konstanz), “On Pause: Suspending Judgment and Abstaining in Machine Learning”

Abstract: Machine Learning (ML) systems typically yield definitive outputs, even when the underlying probabilities do not justify a decision. This poses a significant challenge in medical applications, where patients rely on individualized diagnoses, treatments, and prognoses. A recent advancement in ML research addresses this issue by introducing so-called “abstention models,” which enable ML systems to

Distinguished Speaker Series

Asifa Majid (University of Oxford), “Establishing Human Universals”

Abstract: Psychology, the "science of mental life", aims to provide models and theories that apply universally. However, there is a growing concern that what we gather from studying humans in a particular place and time might not accurately reflect how humans behave in other contexts. This talk will consider how we can establish whether something