Interpretable confidence measures for decision support systems
International Journal of Human-Computer Studies
Published Papers
These are my most recent publications on my research on human-centered AI, specifically Explainable AI.
List of publications
2020
Evaluating XAI: A comparison of rule-based and example-based explanations
Artificial Intelligence
Allocation of Moral Decision-Making in Human-Agent Teams: A Pattern Approach
International Conference on Human-Computer Interaction
2019
Streaming virtual reality video
US patents
Intelligent autonomous vehicles with an extendable knowledge base and meaningful human control
Counterterrorism, Crime Fighting, Forensics, and Surveillance Technologies III
Pluggable Social Artificial Intelligence for Enabling Human-Agent Teaming
NATO HFM symposium on Human Autonomy Teaming
2018
BCI to potentially enhance streaming images to a VR headset by predicting head rotation
Frontiers in Human Neuroscience
Contrastive Explanations for Reinforcement Learning in terms of Expected Consequences
IJCAI-18 Workshop on Explainable AI (XAI)
Using Perceptual and Cognitive Explanations for Enhanced Human-Agent Team Performance
International Conference on Engineering Psychology and Cognitive Ergonomics
Predicting head rotation using EEG to enhance streaming of images to a Virtual Reality headset
2nd International Neuroergonomics Conference
SAIL: a social artificial intelligence layer for human-machine teaming
International Conference on Practical Applications of Agents and Multi-Agent Systems
The SAIL Framework for Implementing Human-Machine Teaming Concepts
International Conference on Practical Applications of Agents and Multi-Agent Systems
Contrastive Explanations with Local Foil Trees
ICML-18 Workshop on Human Interpretability in Machine Learning (WHI'18)
The design and validation of an intuitive confidence measure
In Workshop On Explainable Smart Systems (EXSS)
ICM: An Intuitive Model Independent and Accurate Certainty Measure for Machine Learning.
ICAART '18
2017
An Intelligent Operator Support System for Dynamic Positioning
International Conference on Applied Human Factors and Ergonomics
Human Robot Team Development: An Operational and Technical Perspective
International Conference on Applied Human Factors and Ergonomics
A feasible BCI in real life: Using predicted head rotation to improve HMD imaging
Proceedings of the 2017 ACM Workshop on An Application-oriented Approach to BCI out of the laboratory
2015
Interactive Reinformcement Learning; Two successful solutions for handling an abundance of positive feedback
Radboud University
2013
Connecting the Demons: How connection choices of a Horde implementation affect Demon prediction capabilities.
Radboud University
Current project
MATRX
Ideally, humans and AI work together as a team where they complement each other. Though, to know how such collaboration looks like, it needs to be tested. MATRX is a Python software project that supports the rapid development of team tasks and support their evaluation.
www.matrx-software.com