Validation metrics are key for tracking scientific progress and bridging the current chasm
between artificial intelligence research and its translation into practice. However, increasing …

The full acceptance of Deep Learning (DL) models in the clinical field is rather low with
respect to the quantity of high-performing solutions reported in the literature. End users are …

Over the last decade, neural networks have reached almost every field of science and
become a crucial part of various real world applications. Due to the increasing spread …

Species distribution modeling (SDM) is widely used in ecology and conservation. Currently,
the most available data for SDM are species presence‐only records (available through …

Machine learning (ML) systems are rapidly increasing in size, are acquiring new
capabilities, and are increasingly deployed in high-stakes settings. As with other powerful …

Abstract Graph Neural Networks (GNNs) are powerful machine learning prediction models
on graph-structured data. However, GNNs lack rigorous uncertainty estimates, limiting their …

Continual Learning has inspired a plethora of approaches and evaluation settings; however,
the majority of them overlooks the properties of a practical scenario, where the data stream …

The current evaluation protocol of long-tailed visual recognition trains the classification
model on the long-tailed source label distribution and evaluates its performance on the …

Algorithmic transparency entails exposing system properties to various stakeholders for
purposes that include understanding, improving, and contesting predictions. Until now, most …

Miscalibration--a mismatch between a model's confidence and its correctness--of Deep
Neural Networks (DNNs) makes their predictions hard to rely on. Ideally, we want networks …