Fosca Giannotti
ISTI-CNR Pisa, Italy
Title of the talk
Explainable Machine Learning for Trustworthy Artificial Intelligence
Abstract of the talk
Black box AI systems for automated decision making, often based on machine learning over (big) data, map a user’s features into a class or a score without exposing the reasons why. This is problematic not only for the lack of transparency, but also for possible biases inherited by the algorithms from human prejudices and collection artefacts hidden in the training data, which may lead to unfair or wrong decisions.
The future of AI lies in enabling people to collaborate with machines to solve complex problems. Like any efficient collaboration, this requires good communication, trust, clarity, and understanding. Explainable AI addresses such challenges, and for years different AI communities have studied such topics, leading to different definitions, evaluation protocols, motivations, and results.
This lecture provides a reasoned introduction to the work of Explainable AI (XAI) to date and a quick survey of the literature on machine learning and symbolic AI related approaches. I focus on the urgent open challenge of how to construct meaningful explanations of opaque AI/ML black-box decision systems, introducing our early results on the local-to-global framework as a way towards explainable AI.
Katie Atkinson
University of Liverpool, UK
Title of the talk
Automating Argumentation for Transparently Deciding Legal Cases
Abstract of the talk
Short bio
Katie Atkinson is Professor of Computer Science and Dean of the School of Electrical Engineering, Electronics and Computer Science at the University of Liverpool, UK. Katie is recognised internationally for her research contributions within the field of AI and Law over the past 18 years. Within this area, her specialism is on computational models of argument for modelling legal reasoning. She has published over one hundred and fifty articles in peer-reviewed conference proceedings and journals, and has also applied her work in a variety of collaborative projects with law firms. Her current research is focussed on explainable AI for legal applications. Katie was Program Chair of the fifteenth edition of the International Conference on Artificial Intelligence and Law held in San Diego, USA in 2015 and she served as President of the International Association for Artificial Intelligence and Law (IAAIL) in 2016 and 2017. In 2020 Katie was appointed to serve as a member of the Lawtech UK Panel, a government-backed initiative to help transform the UK legal sector through technology. Katie is also currently serving on the Computer Science and Informatics sub-panel in the UK Research Excellence Framework (REF) 2021.
Carles Sierra
IIIA of CSIC, Spain
Title of the talk
Value engineering
Abstract of the talk
Ethics in Artificial Intelligence is a wide-ranging field which encompasses many open questions regarding the moral, legal and technical issues that arise with the use and design of ethically-compliant autonomous agents. Under this umbrella, the computational ethics area is concerned with the formulation and codification of ethical principles into software components. In this talk, I will take a look at a particular problem in computational ethics: the engineering of moral values into autonomous agents. I will present some results on this area and a vision for future research.
Manuela Naveau
Kunstuniversität Linz, Austria
Title of the talk
CRITICAL DATA and the arts – artistic works in a calculated world
Abstract of the talk
Julie Bernauer
NVIDIA Corporation, USA
Title of the talk
Building and operating a Top10 supercomputer: efficient at scale performance with SuperPODs
Abstract of the talk
Iris von der Tuin
Utrecht University
Title of the talk
AI and Art in the Algorithmic Condition: Interdisciplinarity and Procedural Thinking
Abstract of the talk
FACt speakers
Benoit Macq
Polytechnic School of UCLouvain
Benoit Macq is a professor at the Polytechnic School of UCLouvain. He is now the head of the PILAB Laboratory (Pixels and Interaction Lab) at UCLouvain involved in Artificial Intelligence and Signal Processing applied to image processing.
Benoit Macq has been a researcher at Philips RLB, visiting professor at McGill University in Montreal, Ecole Polytechnique Fédérale de Lausanne, MIT in Boston and Telecom Paris Tech.
Benoit Macq was Prorector of UCL from 2009 to 2014. He was in charge of “Service to Society” and international relations. He was a technological advisor to the Walloon government for the digital transition and co-designed the Digital Wallonia plan. He is co-founder of 11 spin-off companies. He is co-founder of the TRAIL institute with Thierry Dutoit (U-Mons).
Benoit Macq is a Fellow Member of the IEEE, Senior Associate Editor of the IEEE Transactions on Image Processing and Member of the Royal Belgian Academy of Sciences.
Gilles Louppe
University of Liège (Belgium)
Title of the talk
LEGO® Deep Learning
Short bio
intelligence and deep learning at the University of Liège (Belgium).
Previously, he held positions as a Research Fellow at CERN and as a
Postdoctoral Associate at New York University. His research is at the
intersection of machine learning, artificial intelligence and physical
sciences. Together with collaborators, he initiated and developed a
new generation of simulation-based inference algorithms based on deep
learning, with several applications to inference problems from
particle physics, astrophysics, astronomy and gravitational wave
astronomy.
Christoph Schommer
Université du Luxembourg
Future Living with AI and IA
I studied Artificial Intelligence at the German Research Center for Artificial Intelligence in Saarbrücken before working for 8 years at IBM R&D as an IT architect in worldwide service projects in the field of Business Intelligence. At the same time, I completed my doctorate in medical informatics (summa cum laude) at the Goethe University in Frankfurt/Main before being appointed associate professor at the University of Luxembourg in 2003. Today, I lead a research group conducting interdisciplinary research using AI and machine learning technologies. I am a scientific reviewer for Dutch Research Council, Leibniz, Springer, IEEE and for more than 100 conferences (IJCAI, AAMAS, ACM, CogSci, ECML, DHH, and others). I regularly organise lecture series and am the author of about 100 scientific papers. I have (co-)supervised 29 PhD students in Luxembourg, Bologna, Turin and London and given about 150 courses at universities in Luxembourg, Frankfurt, Berlin, Potsdam, Beijing and Singapore. I am also constantly present in newspapers, magazines, radio, television and at schools and do research in numerous projects with industry.
List of accepted submissions
Regular papers
- Benjamin Kap, Marharyta Aleksandrova and Thomas Engel. The Effect of Noise Level on Causal Identification with Additive Noise Models
- Tycho Atsma, Koen van der Zwet and Tom M. van Engers. The effect of group roles on the development of online vaccination Twitter communities
- Johannes Scholtes, Giorgia Nidia Carranza Tejada and Gerasimos Spanakis. An analysis of BERT negation handling in sentiment analysis
- Gaoyuan Liu, Joris De Winter, Bram Vanderborght, Ann Nowé and Denis Steckelmacher. MoveRL: To A Safer Robotic Reinforcement Learning Environment
- Emmanuel Kieffer, Frédéric Pinel, Thomas Meyer, Georges Gloukoviezoff, Hakan Lucius and Pascal Bouvry. Proximal Policy Optimisation for a PrivateEquity Recommitment System
- Ramon Petri, Eugenio Bargiacchi, Huib Aldewereld and Diederik M. Roijers. Heuristic Coordination in Cooperative Multi-Agent Reinforcement Learning
- Pieter Floris Jacobs, Gideon Maillette de Buy Wenniger, Marco Wiering and Lambert Schomaker. Active learning for reducing labeling effort in text classification tasks
- Abdolrahman Khoshrou and Eric J. Pauwels. Matrix Completion using Regularised Matrix Factorisation
- Martijn Oldenhof, Adam Arany, Yves Moreau and Jaak Simm. Self-Labeling of Fully Mediating Representations by Graph Alignment
- Xander Vankwikelberge, Bo Kang, Edith Heiter and Jefrey Lijffijt. ExClus: Explainable Clustering on Low-dimensional Data Representations
- Aras Yurtman, Wannes Meert and Hendrik Blockeel. COBRAS+: Reusing Previously Obtained Constraints in Active Semi-Supervised Clustering
- Nina Hosseini Kivanani, Roberto Gretter, Marco Matassoni and Giuseppe Daniele Falavigna. Experiments of ASR-based mispronunciation detection for children and adult English learners
- Bram De Cooman, Johan Suykens and Andreas Ortseifen. Improving temporal smoothness of deterministic reinforcement learning policies with continuous actions
- Jonas Bei, David Pomerenke, Lukas Schreiner, Sepideh Sharbaf, Pieter Collins and Nico Roos. Explainable AI through the Learning of Arguments
- Paweł Maka, Jelle Jansen, Theodor Antoniou, Thomas Bahne, Kevin Müller, Can Türktas, Nico Roos and Kurt Driessens. Combining Mental Models with Neural Networks
- Bart Bogaerts, Maxime Jakubowski and Jan Van den Bussche. SHACL: A Description Logic in Disguise
- André Mertens and Stylianos Asteriadis. Explainable and Interpretable Features of Emotion in Human Body Expressions
- Mariia Pliusnova and Alexia Briassouli. Deep Learning Techniques for Detection and Diagnosis of Brain Metastases
- Maxime De Bruyn, Ehsan Lotfi, Buhmann Jeska and Walter Daelemans. ConveRT for FAQ Answering
- Nele Albers, Miguel Suau and Frans A. Oliehoek. Using Bisimulation Metrics to Analyze and Evaluate Latent State Representations
- Elizaveta Nekrasova, Tibor Neugebauer, Te Bao and Yohanes Eko Riyanto. Algorithmic Trading in Experimental Markets with Human Traders: A Literature Survey
- Simon Vandevelde and Joost Vennekens. ProbLife: a Probabilistic Game of Life
- Miroslav Kárný and Daniel Karlík. Trust Estimation in Forecasting-Based Knowledge Fusion
- Vinu Ellampallil Venugopal and Sreenivasa Kumar P. Verbalizing but not just Verbatim Translations of Ontology Axioms
- Simona Capponi, Andrew I. Cooper, John Fearnley and Vladimir Gusev. Simple and Fast Methods for Integrating Predicted Data into Bayesian Optimization
- Yu Liuwen, Mirko Zichichi, Réka Markovich and Amro Najjar. Argumentation in Trust Services within a Blockchain Environment
- Rachele Carli. Social robotics and deception: beyond the ethical approach
- Zhao Yang, Mike Preuss and Aske Plaat. Transfer Learning and Curriculum Learning in Sokoban
- Zhao Yang, Mike Preuss and Aske Plaat. Potential-based Reward Shaping in Sokoban
- Timo Kats, Peter van der Putten and Jasper Schelling. Distinguishing Commercial from Editorial Content in News
- Jianing Wang, Matthias Müller-Brockhausen and Aske Plaat. Accelerating Multi-Agent Learning via Centralized Counting and Efficient Hashing
- Nicky Lenaers and Martijn Van Otterlo. Regular Decision Processes for Grid Worlds
- Victoria Bosch, Arne Diehl, Daphne Smits, Akke Toeter and Johan Kwisthout. Implementation of a Distributed Minimum Dominating Set Approximation Algorithm in a Spiking Neural Network
- François Robinet and Raphaël Frank. Refining Weakly-Supervised Free Space Estimation through Data Augmentation and Recursive Training
- Mattias Billast, Tom De Schepper, Kevin Mets, Peter Hellinckx, José Oramas and Steven Latré. Object detection with semi-supervised adversarial domain adaptation for real-time edge devices
- Akash Singh, Kevin Mets, Tom De Schepper, Peter Hellinckx, José Oramas and Steven Latre. Task Independent Capsule-based Agents for Deep Q-Learning
- Augustijn de Boer, Ron Hommelsheim and David Leeftink. A Bayesian Framework for Evaluating Evolutionary Art
- Ouren Kuiper, Martin van den Berg, Joost van der Burgt and Stefan Leijnen. Exploring Explainable AI in the Financial Sector: Perspectives of Banks and Supervisory Authorities
- Niels Rouws, Svitlana Vakulenko and Sophia Katrenko. Dutch SQuAD and Ensemble Learning for Question Answering from Labour Agreements
Encore abstracts
- Sudhanshu Chouhan, Anna Wilbik and Remco Dijkman. A Real-Time Method to Detect Temporal Anomalies in Event Log Data
- Oliver Urs Lenz, Daniel Peralta and Chris Cornelis. Average Localised Proximity: A new data descriptor with good default one-class classification performance
- Marjolein Deryck, Nuno Comenda, Bart Coppens and Joost Vennekens. Combining Logic and Natural LanguageProcessing to Support Investment Management
- Anna Wilbik and Paul Grefen. Towards a Federated Fuzzy Learning System
- Pieter Delobelle, Thomas Winters and Bettina Berendt. RobBERT: a Dutch RoBERTa-based Language Model
- Gonzalo Nápoles, Agnieszka Jastrzebska and Yamisleydi Salgueiro. A Note on Pattern Classification with Evolving Long-term Cognitive Networks
- Azqa Nadeem, Sicco Verwer, Stephen Moskal and Shanchieh Jay Yang. SAGE: Intrusion Alert-driven Attack Graph Extractor
- Hans van Ditmarsch, Malvin Gattinger and Rahim Ramezanian. Everyone knows that everyone knows (abstract)
- Felipe Kenji Nakano, Konstantinos Pliakos and Celine Vens. Deep tree-ensembles for multi-output prediction
- Leandra Fichtel, Jan-Christoph Kalo and Wolf-Tilo Balke. Prompt Tuning or Fine-Tuning -Investigating Relational Knowledge in Pre-Trained Language Models
- Yihe Dong, Jean-Baptiste Cordonnier and Andreas Loukas. Attention is not all you need: pure attention loses rank doubly exponentially with depth
- Isel Grau, Ann Nowe and Wim Vranken. Encore Abstract: Interpreting a Black-Box Predictor to Gain Insights into Early Folding Mechanisms
- Kylian Van Dessel, Jo Devriendt and Joost Vennekens. FOLASP: FO(.) as Input Language for Answer Set Solvers
- Victor Contreras, Reyhan Aydogan, Amro Najjar and Davide Calvaresi. On Explainable Negotiations via Argumentation
- Luisa Ebner, Malte Nalenz, Annette ten Teije, Frank van Harmelen and Thomas Augustin. Expert RuleFit: Complementing Rule Ensembles with Expert Knowledge
- Anna Lukina, Christian Schilling and Thomas Henzinger. Active Monitoring of Neural Networks
- V. Javier Traver, Judith Zorío and Luis A. Leiva. A Gaze-Based Measure of Temporal Salience
- Reza Refaei Afshar, Jason Rhuggenaath, Yingqian Zhang and Uzay Kaymak. Optimizing Reserve Price using Deep Reinforcement Learning and Shaped Reward
- Yazan Mualla, Igor Tchappi, Timotheus Kampik, Amro Najjar, Davide Calvaresi, Abdeljalil Abbas-Turki, Stéphane Galland and Christophe Nicolle. A Human-Agent Architecture for Explanation Formulation (An extended abstract)
- Johan Kwisthout. Explainable AI using MAP-independence
- Eugenio Bargiacchi, Timothy Verstraeten and Diederik M. Roijers. Scalable Multi-Agent Reinforcement Learning with Cooperative Prioritized Sweeping
- Daniël Vos and Sicco Verwer. Efficient Training of Robust Decision Trees Against Adversarial Examples
- Zahra Atashgahi, Ghada Sokar, Tim van der Lee, Elena Mocanu, Decebal Constantin Mocanu, Ramond Veldhuis and Mykola Pechenizkiy. Quick and Robust Feature Selection: the Strength of Energy-efficient Sparse Training for Autoencoders (Extended Abstract)
- Davide Ceolin, Giuseppe Primiero, Jan Wielemaker and Michael Soprano. Assessing the Quality of Online Reviews using Formal Argumentation Theory
- Neil Yorke-Smith. Agent-Based Simulation of Short-Term Peer-to-Peer Rentals: Evidence from the Amsterdam Housing Market
- Paulo Roberto de Oliveira da Costa, Yingqian Zhang, Alp Akcay and Uzay Kaymak. Learning 2-opt Local Search from Demonstrations
- Ghada Sokar, Decebal Constantin Mocanu and Mykola Pechenizkiy. SpaceNet: Make Free Space For Continual Learning (Extended Abstract)
- Oliver Roesler and Elahe Bagheri. Unsupervised Online Grounding for Social Robots (Extended Abstract)
Posters and demos
- Hélène Plisnier, Alessandro Fasano and Ann Nowé. Play the Reinforcement Learning Agent
- Mani Tajaddini, Willem-Paul Brinkman, Annette ten Teije and Mark Neerincx. A Design Pattern Language for Hybrid Intelligent Teams
- Hélène Plisnier, Denis Steckelmacher and Ann Nowé. Shepherd: Reinforcement Learning as a Service with Distributed Execution
- Nele Albers, Mark A. Neerincx and Willem-Paul Brinkman. Reinforcement Learning-Based Persuasion by a Conversational Agent for Behavior Change
- Kristina Kudryavtseva and Sviatlana Hoehn. SafeTraveller – A conversational assistant for BeNeLux travellers
- Marjolein Deryck, Nuno Comenda, Bart Coppens and Joost Vennekens. Logical Reasoning application with NLP interface to construct the Knowledge Base
- Imen Chakroun, Tom Vander Aa, Roel Wuyts and Wilfried Verarcht. Using privacy preserving amalgamated machine learning for pedestrian safety in warehouses
- Dimitra Anastasiou, Anders Ruge, Hoorieh Afkari, Patrick Gratz, Radu Ion, Verginica Barbu Mititelu, Olivier Pedretti, Svetlana Segarceanu and George Suciu. A Machine Translation powered AI Chatbot
- Isel Grau, Luis Daniel Hernandez, Astrid Sierens, Simeon Michel, Nico Sergeyssels, Vicky Froyen, Catherine Middag and Ann Nowe. Talking to your Data: Interactive and interpretable data mining through a conversational agent
- Roelant Ossewaarde, Stefan Leijnen and Thijs Van den Berg. An invariants based architecture for combining small and large data sets in neural networks.
Thesis abstracts
- Wafaa Aljbawi. Automated Diagnostic System of Skin Cancer using Deep Convolutional Neural Networks on Dermoscopic Images
- Sven van Asseldonk and Itir Onal Ertugrul. Deepfake Video Detection using Deep Convolutional and Hand-Crafted Facial Features with Long Short-Term Memory Network
- Chris Slewe, Maaike de Boer and Tejaswini Deoskar. Generating common-sense scene graphs using a knowledge base BERT model
- Martin Toman and Neil Yorke-Smith. Localised Reputation in the Prisoner’s Dilemma
- Abigail Vella, Frankie Inguanez and Daren Scerri. Remote NO2 emissions assessment during COVID-19 lockdowns
- Adel Magra, Peter Spreij, Tim Baarslag and Michael Kaisers. Automated Negotiation Under User Preference Uncertainty
- Astrid Sierens, Isel Grau, Luis Daniel Hernandez, Simeon Michel, Vicky Froyen, Catherine Middag and Ann Nowe. Thesis Abstract: Interactive Subgroup Discovery for the conversational data governance platform “Talking to your Data”
- Aleksandra Olczyk and Itir Onal Ertugrul. Pain recognition from thermal videos using deep neural networks
- Domien Hennion, Timothy Verstraeten and Ann Nowé. Safe Fleet-Wide Policy Iteration
- Lisa Koutsoviti Koumeri and Gonzalo Nápoles. Bias quantification measures based on fuzzy rough sets
- Gregory Wullaert, Fabian Sanjines, Timothy Verstraeten and Ann Nowé. Learning Deep Coordination Graphs for Multi-Agent Systems
- Julian Posch, Kurt Driessens and Jacques Verriet. Encoder-Decoder Approaches for Detection and Diagnosis of Anomalies in Machine Control Applications
- Anna-Maria Angelova, Fernando P. Santos and Sandro Bjelogrlic. Enhancing Reject Inference in Credit Scoring with Selective Semi-Supervised Learning
- Floris Doolaard and Neil Yorke-Smith. Online Learning of Deeper Variable Ordering Heuristics for Constraint Optimisation Problems
- Yazan Mualla, Stéphane Galland and Christophe Nicolle. Explaining the Behavior of Remote Robots to Humans (Extended abstract)
- Pietro Piccini. Identifying strong predictors of engagement in Facebook news posts
- Songha Ban and Lee-Ling Sharon Ong. Producing “Open-Style” Choreography for K-Pop Music with Deep Learning
- Valerie S. Sawirja and Peter Bloem. Fine-Tuning Pretrained Language Models for Controlled Text Generation with Adapters
- Thomas Vaeyens, Youri Coppens, Timothy Verstraeten and Ann Nowe. Explainable Reinforcement Learning for Fleet Applications
- Matthias Cami, Inês Terrucha, Yara Khaluf and Pieter Simoens. Bayesian Inverse Reinforcement Learning for strategy extraction in the iterated Prisoner’s Dilemma game
- Michela Venturini and Giulia Barbati. Clinical Predictive Models: