Connectivity Fund

Towards Explainable and Unsupervised Concept Discovery for Flood DetectionTowards Explainable and Unsupervised Concept

Ivica Obadic Chair of Data Science in Earth Observation at the Technical University of Munich Extreme weather events and climate changes increase the need for automated flood detection systems. In recent years, the deep learning models trained on earth observation data became promising approach for this problem producing state-of-the-art predictive results. Nevertheless, their usage in …

Towards Explainable and Unsupervised Concept Discovery for Flood DetectionTowards Explainable and Unsupervised Concept Read More »

Samples Selection with Group Metric for Experience Replay in Continual Learning

Andrii Krutsylo PhD student at the Institute of Computer Science of the Polish Academy of Sciences The study aims to reduce the decline in performance of a model trained incrementally on non-i.i.d. data, using replay-based strategies to retain previous task knowledge. To address limitations in existing variations, which only select samples based on individual properties, …

Samples Selection with Group Metric for Experience Replay in Continual Learning Read More »

Large Scale Combinatorial Graybox Optimization

Lorenzo Canonne PhD student at Inria The field of gray box optimization has led to the design of new operators capable of using the structural information of problems; these operators are now the basis of powerfulmeta-heuristics. For large-scale NK landscapes, many operators have been proposed and iterated local search combined with gray box crossovers is …

Large Scale Combinatorial Graybox Optimization Read More »

Making big benchmarks more trustworthy: Identifying the capabilities and limitations of language models by improving the BIG-Bench benchmark

Ryan Burnell Postdoctoral Research Fellow at Leverhulme Centre for the Future of Intelligence, University of Cambridge, UK AI systems are becoming an integral part of every aspect of modern life. To ensure public trust in these systems, we need tools that can be used to evaluate their capabilities and weaknesses. But these tools are struggling …

Making big benchmarks more trustworthy: Identifying the capabilities and limitations of language models by improving the BIG-Bench benchmark Read More »

Learning Neural Algebras

Pedro Zuidberg Dos Martires Postdoctoral Researcher at Örebro University (Sweden) Abstract algebra provides a formalism to study sets and how the elements of these sets relate to each other by defining relations between set elements. Abstract algebraic structures are abundantly present in artificial intelligence. For instance, Boolean algebra constitutes the bedrock of symbolic AI. Interestingly, …

Learning Neural Algebras Read More »

Learning trustworthy models from positive and unlabelled data

Pawel Teisseyre Assistant Professor at the Polish Academy of Sciences The goal of the research stay is to explore learning classification models using positive-unlabelled (PU) data. In PU learning, it is assumed that only some observations in training data are assigned label, which is positive, whereas the remaining observations are unlabelled and can be either …

Learning trustworthy models from positive and unlabelled data Read More »

A Modular Framework for Hybrid Participatory Systems

Enrico Liscio – TU Delft PhD student Participatory systems aim to elicit citizens’ stances on societal discussions to inform policy making. In particular, human values are a crucial component of citizens’ stances, since they are the drivers of our opinions and behaviors. AI can enable mass participation and process large quantity of citizens’ input. However, …

A Modular Framework for Hybrid Participatory Systems Read More »

Trustworthy AI for human behavior prediction by autonomous

Julian F. Schumann – TU Delft PhD student For humans to trust autonomous vehicles, they need to have confidence in the vehicles’ ability to reliably resolve space-sharing conflicts with other traffic participants in a safe manner – such as in the case of crossing or merging paths. Planning safe and efficient interactions for autonomous vehicles …

Trustworthy AI for human behavior prediction by autonomous Read More »

Graph Gaussian Processes for Interactive Robot Task Learning

Giovanni Franzese – TU Delft PhD candidate The adaptability of robot manipulators to many different tasks is currently constrained by systematic hard coding of each specific task. Recent machine learning methods like Learning from Demonstrations (LfD) and Reinforcement Learning (RL) have shown promising results in having fast reprogramming of the task using human demonstrations or …

Graph Gaussian Processes for Interactive Robot Task Learning Read More »