Deep neural networks often rely on spurious correlations to make predictions, which hinders
generalization beyond training environments. For instance, models that associate cats with …

Reliable deployment of machine learning models such as neural networks continues to be
challenging due to several limitations. Some of the main shortcomings are the lack of …

Part-prototype Networks (ProtoPNets) are concept-based classifiers designed to achieve the
same performance as black-box models without compromising transparency. ProtoPNets …

Abstract Neuro-Symbolic (NeSy) predictive models hold the promise of improved
compliance with given constraints, systematic generalization, and interpretability, as they …

The rise of intelligent systems and smart spaces has opened up new opportunities for
human–machine collaborations. Interactive Machine Learning (IML) contribute to fostering …

Goal misalignment, reward sparsity and difficult credit assignment are only a few of the many
issues that make it difficult for deep reinforcement learning (RL) agents to learn optimal …

Explanations in interactive machine-learning systems facilitate debugging and improving
prediction models. However, the effectiveness of various global model-centric and data …

We introduce Neuro-Symbolic Continual Learning, where a model has to solve a sequence
of neuro-symbolic tasks, that is, it has to map sub-symbolic inputs to high-level concepts and …

Despite being highly performant, deep neural networks might base their decisions on
features that spuriously correlate with the provided labels, thus hurting generalization. To …

While traditional deep learning models often lack interpretability, concept bottleneck models
(CBMs) provide inherent explanations via their concept representations. Specifically, they …