Research Day on Responsible AI
Join the Antwerp Center on Responsible AI (ACRAI) for a research day featuring expert talks on responsible AI. A wide range of topics will be explored: machine learning, law, robotics, and many more. Come and discover diverse perspectives on the future of technology!
Praktische info:
Georganiseerd door:
Leertrajecten
ACRAI, the Antwerp Center for Responsible AI, is a cutting-edge research center dedicated to advancing the field of responsible AI.
Located in the vibrant city of Antwerp, Belgium, ACRAI is at the
forefront of the rapidly growing field of responsible AI, bringing
together researchers to tackle some of the most pressing issues related
to AI's impact on society.
The center's mission is to promote the development, application, and dissemination of responsible AI in a wide array of domains, including health, tax, insurance, etc. To achieve this goal, ACRAI conducts groundbreaking research, fosters collaboration among stakeholders, and provides expert guidance and training on responsible AI.
The interdisciplinary team of researchers at ACRAI brings together
expertise in computer science, law, philosophy, sociology, and other
relevant fields to address the multifaceted challenges posed by AI.
Their research covers a broad range of topics, including bias and
discrimination in AI, explainability, transparency, accountability,
privacy and data protection, sustainability, and AI governance.
At this research day, presentations will be given by researchers from various disciplines on a variety of topics -- all tied to responsible AI:
Research Day Schedule
9:20-9:30 Introduction - Prof. Martens & Prof. Calders
9:30-10:45 Block 1 - Presentations 1-3
10:45-11:05 Coffee Break
11:05-12:20 Block 2 - Presentations 4-6
12:20-13:30 Lunch Break
13:30-14:40 Block 3 - Presentations 7-9
14:40-15:00 Coffee Break
15:00-16:15 Block 4 - Presentations 10-12
16:15-17:30 Reception
Presenters
- Mateusz Cedro on Narratives to Explain AI Models
- Kimberly Van Sande on Taxation of AI
- Salma Haidar & José Oramas on Explainability-based Band Selection for Hyperspectral Image Analysis
- Prof. Jan Blockx & Benjamin González on AI and Antitrust Law
- Siemen Herremans on Robust Reinforcement Learning with Adversarial Auxiliary Model
- Hamed Behzadi-Khormouji & José Oramas on Deep Model Interpretation with Limited Data
- Marco Favier on Machine Learning Fairness and its Pitfalls
- Dr Daphne Lenders & Anne Oloo on Algorithmic Fairness in Computer Science and Law
- Nicolae Banari on Challenges in LLM Hallucinations
- Prof. Gert-Jan de Bruijn on Chatbots and Responsible AI
- Jakob Raymaekers on Linear Model Trees
- Doreen Jirak on Human-Robot Interactions
Deep Model Interpretation with Limited Data
Hamed Behzadi-Khormouji & José Oramas
In this talk, we present an approach to exploit "dataset summaries", produced via Coreset Selection Algorithms, as a means to reduce the computational costs of model interpretation algorithms. Thus, allowing the frequent application of these interpretation methods during the development and training of a model; enabling their use as a tool for debugging.
Explainability-based Band Selection for Hyperspectral Image Analysis
Salma Haidar & José Oramas
In this talk, in the context of Hyperspectral Image Analysis (HSI), we present how insights extracted from Explainability Algorithms can help the selection of most relevant information (bands) from the input. Thus, enabling the development of HSI systems with shorter image acquisition and processing times and lower memory requirements.
Lesgevers / sprekers
Mateusz Cedro
AI Research Scientist and PhD student in Explainable AI, specializing in Graph Neural Networks at the University of Antwerp, Belgium. Conducting research within the Applied Data Mining Research Group, I deliver Machine Learning and AI solutions for both research and business contexts. My expertise lies in building and explaining complex ML/AI models (XAI), data inference, and visualization. I’m passionate about collaborating with diverse teams to drive data-driven insights and innovations
Kimberly Van Sande
Mandaatassistent fiscaal recht Universiteit Antwerpen
PhD: artificial intelligence, AI-robots and taxation
Salma Haider
Salma Haidar is a PhD candidate at the University of Antwerp in Belgium, specializing in advanced representation learning for hyperspectral images, with a focus on land cover analysis from remote sensing data. She holds a bachelor's degree in Accounting and Finance from the Lebanese University and a Master's in Money and Banking from the American University of Beirut. She also holds a Postgraduate Diploma in Big Data & Analytics from KU Leuven. A Chartered Financial Analyst (CFA) since 2006, her diverse background enhances her contributions to machine learning and hyperspectral image analysis.
José Oramas
José Oramas is an Assistant Professor at the Internet Data Lab (IDLab) a joint research lab between the University of Antwerp and IMEC. He received his PhD at the Center for Processing Speech and Images (ESAT-PSI) of KU Leuven in April 2015. Earlier he received his engineering degree from Escuela Superior Politecnica del Litoral in Ecuador. During his Ph.D. he conducted research on understanding how groups of elements from the image (objects, object-parts, image regions, trajectories, etc.) interact and how the relationships between them can be exploited to improve artificial visual perception problems. This fueled his interest towards investigating exploratory/explanatory models that can identify informative intermediate representations and use them as means to justify the predictions that they make.
Research Interests: Representation Learning, Interpretability and Explainability, Multiple Instance Learning, Machine Learning, Deep Learning and Computer Vision
Jan Blockx
Mijn onderzoek gaat vooral over Europees economisch recht. Het omvat domeinen als mededingingsrecht, staatssteun, de interne markt, Europees handelsbeleid en technologieregulering. Daarbij maak ik gebruik van theoretische inzichten uit recht en filosofie, alsook van mijn praktische ervaring. Naast mijn academische werk, ben ik assessor bij de Belgische mededingingsautoriteit. Ik heb ook tien jaar als advocaat gewerkt bij de internationale advocatenkantoren Freshfields en Hogan Lovells.
Benjamin González
PhD Researcher in Competition Law & Artificial Intelligence
Siemen Herremans
PhD researcher, IDLab Antwerp, University of Antwerp - imec
Hamed Behzadi-Khormouji
PhD Researcher at imec-IDLab (UAntwerpen - imec)
Expertise: Deep Model Explanation & Interpretation, AI Medical Imaging
Marco Favier
PhD student 'Fairness in ML' at University of Antwerp
Daphne Lenders
AI Researcher at Scuola Normale Superiore | PhD
- Researcher associated with Horizon-Europe funded project TANGO: https://tango-horizon.eu/
- Developing novel methods for ethical Human-AI collaboration & evaluating them on real-world use cases
Anne Oloo
PhD Researcher and Teaching Assistant in human rights law at University of Antwerp
My PhD research is on algorithmic human rights accountability and focusses on inclusive regulation of online global media platforms.
Nicolae Banari
Senior Researcher in AI | PhD
Development of industrial AI projects at University of Antwerp.
Key projects:
- Explainable multimodal recommendation system for automated outfit choices.
- Legal AI assistant.
Gert-Jan de Bruijn
De focus van mijn onderzoek is het toepassen van nieuwe technologische mogelijkheden en innovaties voor communicatiewetenschappelijke doeleinden. Deze technologische innovaties omvatten, maar zijn niet beperkt tot, Virtual Realities, gespreks- en sociale agentsystemen, geautomatiseerde tekstanalyse en tekstgeneratie, sensor data (GPS, hartslagmeters) en automatische (sociale)netwerkanalyse.Ik gebruik deze innovaties in een breed communicatiewetenschappelijk domein, zoals de ontwikkeling en evaluatie van chatbots die automatisch met mensen communiceren voor informatieve doeleinden (het omboeken van vliegtickets), maar ook chatbots die menselijke counseling taken overnemen (zoals ondersteuning bij het stoppen met roken). Ik onderzoek ook hoe ontwikkelingen op het gebied van Natural Language Processingen en Natural Language Understanding kunnen bijdragen om inhoud van nieuws en sociale media automatisch te classiferen, hoe virtual reality technieken kunnen bijdragen aan effectievere trainingen (bijvoorbeeld hoe artsen beter kunnen communiceren met patienten), en hoe near-field communicatie en geo-info gebruikt kunnen worden om effectiever en efficienter te communiceren. Daarnaast heb ik een sterke expertise in een breed scala aan onderzoeksmethoden, waaronder experimentele design, gerandomiseerde trials, focusgroep interviews en meta-analyses en systematische reviews.Mijn onderzoek wordt gesponsord door een groot aantal competitieve grant (totaal >21 miljoen EUR) van nationaal wetenschappelijke organisaties en Horizon2020.
Jakob Raymaekers
Mijn expertise omvat: multivariate statistiek, robuuste statistiek, anomaly detection, clustering, visualisatie, statistische machine learning
Doreen Jirak
Senior Researcher at the Department of Product Development, University of Antwerp, working in the AHOI project studying the impact of human factors and explainable AI (XAI) in autonomous systems.
Gerelateerde opleidingen
Preparation for AI: From Raw Data to Reliable Models | How to make your data AI-ready
Opleiding - Brugge - PUC - KU Leuven Continue