June 2023

Improving inverse abstraction based neural network verification using automated machine learning techniques

Matthias könig PhD at Leiden University Abstract: This project seeks to advance the state of the art in formal neural network verification. Formal neural network verification methods check whether a trained neural network, for example an image classifier, satisfies certain properties or guarantees regarding its behaviour, such as correctness, robustness, or safety, under various inputs

Improving inverse abstraction based neural network verification using automated machine learning techniques Read More »

Towards Stable and Robust Learning with Limited Labelled Data: Investigating the Impact of Data Choice

Branislav Pecher PhD at Kempelen Institute of Intelligent Technologies, member of Slovak.AI Abstract: Learning with limited labelled data, such as meta-learning, transfer learning or in-context learning, aims to effectively train a model using only a small amount of labelled samples. However, there is still limited understanding of the required settings or characteristics for these approaches

Towards Stable and Robust Learning with Limited Labelled Data: Investigating the Impact of Data Choice Read More »

BEYOND CHATGPT: Europe needs to act now to ensure technological sovereignty in Next-Generation AI – Call for Action following the EU Parliament Meeting

On May 25th, 2023 TAILOR made its contribution to the event Beyond ChatGPT: How can Europe get in front of the pack on Generative AI Models?, organised by a broad consortium of European projects and Institutions: the HumanE-AI-Net European Network of Centres of Excellence in Artificial Intelligence, the International Research Centre on Artificial Intelligence (IRCAI) under the

BEYOND CHATGPT: Europe needs to act now to ensure technological sovereignty in Next-Generation AI – Call for Action following the EU Parliament Meeting Read More »