5 papers
GenFacts-Generative Counterfactual Explanations for Multi-Variate Time Series
Sarah Seifi, Anass Ibrahimi, Tobias Sukianto +3
Counterfactual explanations aim to enhance model transparency by showing how inputs can be minimally altered to change predictions. For multivariate time series, existing methods o…
Learning Interpretable Rules from Neural Networks: Neurosymbolic AI for Radar Hand Gesture Recognition
Sarah Seifi, Tobias Sukianto, Cecilia Carbonelli +2
Rule-based models offer interpretability but struggle with complex data, while deep neural networks excel in performance yet lack transparency. This work investigates a neuro-symbo…
Complying with the EU AI Act: Innovations in Explainable and User-Centric Hand Gesture Recognition
Sarah Seifi, Tobias Sukianto, Cecilia Carbonelli +2
The EU AI Act underscores the importance of transparency, user-centricity, and robustness in AI systems, particularly for high-risk systems. In response, we present advancements in…
LiRCDepth: Lightweight Radar-Camera Depth Estimation via Knowledge Distillation and Uncertainty Guidance
Huawei Sun, Nastassia Vysotskaya, Tobias Sukianto +5
Recently, radar-camera fusion algorithms have gained significant attention as radar sensors provide geometric information that complements the limitations of cameras. However, most…
Interpretable Rule-Based System for Radar-Based Gesture Sensing: Enhancing Transparency and Personalization in AI
Sarah Seifi, Tobias Sukianto, Cecilia Carbonelli +2
The increasing demand in artificial intelligence (AI) for models that are both effective and explainable is critical in domains where safety and trust are paramount. In this study,…