lena.tasse, Author at TAILOR

The TAILOR roadmap shows the path towards Trustworthy AI

6 September 2022

The TAILOR project is focussed on Trustworthy Artificial Intelligence through Learning, Optimization and Reasoning, and address topics that are currently very actively investigated. Therefore, defining a roadmap was an ambitious endeavour. The editorial team led by Marc Schoenauer, INRIA, France and Michela Milano, Bologna University have assembled voices from the TAILOR network and beyond to […]

The TAILOR roadmap shows the path towards Trustworthy AI Read More »

Rich Sutton and the Alberta Plan for AI Research

24 August 2022

Rich Sutton, professor at the department of Computing Science at Alberta University, will give a keynote speak at the upcoming TAILOR conference in Prague, 13-14 September 2022. The keynote is organised as a joint event with the outreach event Prague Computer Science Seminar. Abstract The keynote will present the Alberta Plan for AI research, based

Rich Sutton and the Alberta Plan for AI Research Read More »

Deep fake videos detection through Explainable AI

17 August 2022

Aiming towards combating the challenges faced by fake video detection, the prime objective of this research is to develop a proactive, advanced explainable, human collaborated AI-based online disinformation detecting tool for securing a trustworthy social media environment.

Deep fake videos detection through Explainable AI Read More »

A “sound off” video for noisy environments and social media

14 August 2022

The following video has been produced by WP12 and is availble upon request for anyone who would like to use it to promote the network. It’s ideal to be used as on a monitor during events such as fairs or other meetings or social media.

A “sound off” video for noisy environments and social media Read More »

Learning to Run a Power Network Challenge (L2RPN)

2 June 2022

The “Learning to run a power network challenge 2022” is concerned with AI for smart grids, and it has been built by RTE, the French Power Grid operator, and the TAU team, in collaboration with EPRI, CHA Learn, Google research, UCL and IQT labs.

Learning to Run a Power Network Challenge (L2RPN) Read More »

A TAILOR paper selected for oral presentation at CVPR 2022

20 May 2022

A paper on learning from a limited data for human body/pose estimation from TAILOR researcher Hossein Rahmani, Lancaster University, has been accepted in the IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR 2022) for oral presentation (acceptance rate is ~4%). This work has been done in collaboration with researchers from Singapore, US and

A TAILOR paper selected for oral presentation at CVPR 2022 Read More »

Logic-based multi-agent reinforcement learning

21 March 2022

Brian Logan Associate Professor at Utrecht University Many activities that are easy for humans, such as walking together with other humans, are hard to program as a set of rules for Artificial Intelligence (AI) robots. This is why machine learning is so popular in AI: correct behaviour can be learned by trial and error. However,

Logic-based multi-agent reinforcement learning Read More »

Conformal Inference for multivariate, complex, and heterogeneous data

21 March 2022

Marcos Matabuena University of Santiago de Compostela In this project, in collaboration with Gábor Lugosi (UPF), we propose new uncertainty quantification methods based on the design of new Conformal Inference strategies for complex data that arise in modern personalized medicine applications. The new uncertainty methods can examine the reliability and safety of results obtained with

Conformal Inference for multivariate, complex, and heterogeneous data Read More »

Neuro-symbolic integration for graph data

21 March 2022

Manfred Jaeger Associated Professor at Aalborg University From Social networks to bibliographic databases: many important real-world phenomena consist of networks of connected entities. The mathematical model of such networks is that of a graph, which in its basic form just consists of a collection of nodes that are connected by edges. To model the rich

Neuro-symbolic integration for graph data Read More »

Private Continual Learning from a Stream of Pretrained Models

21 March 2022

Antonio Carta Post-doc at Pisa University Learning continually from non-stationary data streams is a challenging research topic of growing popularity in the last few years. Being able to learn, adapt and generalize continually, in an efficient, effective and scalable way appears to be fundamental for a more sustainable development of Artificial Intelligent systems. However, access

Private Continual Learning from a Stream of Pretrained Models Read More »