May 2023

Report from TDW “AI for Future Energy & Sustainability”

The Joint Theme Development Workshop (TDW) co-organised by CLAIRE, TAILOR and VISION on “AI for Future Energy & Sustainability” took place on the 23rd of February 2023 with the aim to develop and identify the most promising and emerging AI topics in the Energy sector. At this one-day workshop, experts from academia, industry and politics jointly developed initial input for […]

Report from TDW “AI for Future Energy & Sustainability” Read More »

WP4 workshop at NeSy2023 conference in Siena, 3-5 July 2023

NeSy2023 conference (https://sites.google.com/view/nesy2023/home?authuser=0) will host a TAILOR WP4 workshop on July 3rd, 11:00-13:00, about “Benchmarks for Neural-Symbolic AI”. The workshop will be in hybrid format, however in-person participation is strongly suggested, especially for NeSy researchers and PhD students. For more information, we recommend to visit the webpage https://sailab.diism.unisi.it/tailor-wp4-workshop-at-nesy/. Abstract The study of Neural-Symbolic (NeSy) approaches has

WP4 workshop at NeSy2023 conference in Siena, 3-5 July 2023 Read More »

TAILOR Initiates Roadmapping Activities to Ensure Trustworthy AI Systems

The TAILOR project has continued its roadmapping activities by conducting a thematic workshop centred around addressing crucial questions regarding the trustworthiness of AI. Key areas of focus during the workshop included developing methods for measuring and quantifying TAI, generating trust through certifications, and identifying the mentoring and training required to enhance trustworthiness. A key point

TAILOR Initiates Roadmapping Activities to Ensure Trustworthy AI Systems Read More »

Fostering Appropriate Trust in Predictive Policing AI Systems

Siddharth Mehrotra PhD student at TU Delft The use of AI in law enforcement, particularly in predictive policing, raises concerns about bias, discrimination, and infringement of civil liberties. Building appropriate trust in these systems is crucial to address these concerns and ensure ethical use. In this research proposal, we aim to investigate how explanations generated

Fostering Appropriate Trust in Predictive Policing AI Systems Read More »

Meta-learning for Continual Learning

Anna Vettoruzzo PhD student at the Halmstad University Continual learning (CL) refers to the ability to continually learn over time by accommodating new knowledge while retaining previously learned experiences. While this concept is inherent in the human learning ability, current machine learning-based methods struggle with this as they are highly prone to forget past experiences

Meta-learning for Continual Learning Read More »

Deep reinforcement learning for predictive monitoring under LTLf constraints

Efrén Rama Maneiro PhD student at the University of Santiago de Compostela Predictive monitoring is a subfield of process mining that focuses on predicting how a process will unfold. Deep learning techniques have become popular in this field due to their enhanced performance with respect to classic machine learning models. However, most of these approaches

Deep reinforcement learning for predictive monitoring under LTLf constraints Read More »

Data-Centric AutoML and Benchmarks with Optimal Transport

Prabhant Singh Research Engineer at TU Eindhoven Automated machine learning (AutoML) aims to make easier and more accessible use of machine learning algorithms for researchers with varying levels of expertise. However, AutoML systems, including classical ones such as Auto-Sklearn and Neural Architecture Search (NSGANet, ENAS, DARTS), still face challenges with starting from scratch for their

Data-Centric AutoML and Benchmarks with Optimal Transport Read More »

Multi-Objective Rating Systems

Paolo Turrini Associate Professor at the Department of Computer Science, University of Warwick This project studies rating systems with multiple objectives, where users are matched to items in order to satisfy several desirable properties. In particular, it looks beyond classical Pareto efficiency, modelling and studying allocations that satisfy fairness, diversity and reliability. This project will

Multi-Objective Rating Systems Read More »

Optimal training of a structured ensemble of Binarized Neural Networks with Mixed-Integer Linear Programming techniques

Simone Milanesi, Ambrogio Maria Bernardelli PhD students at the CompOpt Lab (University of Pavia) Binarized Neural Networks (BNNs) are receiving increasing attention due to their lightweight architecture and ability to run on low-power devices.The Mixed-Integer Linear Programming (MILP) approach achieves the state of the art for training classification BNNs when limited data are available.We propose

Optimal training of a structured ensemble of Binarized Neural Networks with Mixed-Integer Linear Programming techniques Read More »