3 citations · 6 across the 4 of their papers we have counts for
4 papers · 1 filter
DiConStruct: Causal Concept-based Explanations through Black-Box Distillation
Ricardo Moreira, Jacopo Bono, Mário Cardoso +3
Model interpretability plays a central role in human-AI decision-making systems. Ideally, explanations should be expressed using human-interpretable semantic concepts. Moreover, th…
Lightweight Automated Feature Monitoring for Data Streams
João Conde, Ricardo Moreira, João Torres +5
Monitoring the behavior of automated real-time stream processing systems has become one of the most relevant problems in real world applications. Such systems have grown in complex…
ConceptDistil: Model-Agnostic Distillation of Concept Explanations
João Bento Sousa, Ricardo Moreira, Vladimir Balayan +2
Concept-based explanations aims to fill the model interpretability gap for non-technical humans-in-the-loop. Previous work has focused on providing concepts for specific models (eg…
Data+Shift: Supporting visual investigation of data distribution shifts by data scientists
João Palmeiro, Beatriz Malveiro, Rita Costa +3
Machine learning on data streams is increasingly more present in multiple domains. However, there is often data distribution shift that can lead machine learning models to make inc…