11 papers
Explainable Artificial Intelligence Techniques for Interpretation of Food Models: a Review
Leonardo Arrighi, Ingrid Alves de Moraes, Marco Zullich +3
Artificial Intelligence (AI) has become essential for analyzing complex data and solving highly-challenging tasks. It is being applied across numerous disciplines beyond computer s…
On the Properties of Feature Attribution for Supervised Contrastive Learning
Leonardo Arrighi, Julia Eva Belloni, Aurélie Gallet +3
Most Neural Networks (NNs) for classification are trained using Cross-Entropy as a loss function. This approach requires the model to have an explicit classification layer. However…
No Single Metric Tells the Whole Story: A Multi-Dimensional Evaluation Framework for Uncertainty Attributions
Emily Schiller, Teodor Chiaburu, Marco Zullich +1
Research on explainable AI (XAI) has frequently focused on explaining model predictions. More recently, methods have been proposed to explain prediction uncertainty by attributing…
Enhancing Tree Species Classification: Insights from YOLOv8 and Explainable AI Applied to TLS Point Cloud Projections
Adrian Straker, Paul Magdon, Marco Zullich +5
Aiming to advance research in the field of interpretability of deep learning models for tree species classification using TLS 3D point clouds we present insights in the classificat…
Uncertainty in Semantic Language Modeling with PIXELS
Stefania Radu, Marco Zullich, Matias Valdenegro-Toro
Pixel-based language models aim to solve the vocabulary bottleneck problem in language modeling, but the challenge of uncertainty quantification remains open. The novelty of this w…
Sparsity-Driven Plasticity in Multi-Task Reinforcement Learning
Aleksandar Todorov, Juan Cardenas-Cartagena, Rafael F. Cunha +2
Plasticity loss, a diminishing capacity to adapt as training progresses, is a critical challenge in deep reinforcement learning. We examine this issue in multi-task reinforcement l…