Achieving high reliability in AI systems—such as autonomous vehicles that stay on course even in snowstorms or medical AI ...

Currently, deep learning is the most important technique for solving many complex machine vision problems. State-of-the-art deep learning models typically contain a very large number of parameters ...

Abstract Model robustness indicates a model's capability to generalize well on unforeseen distributional shifts, including data corruptions and ...

The task of point cloud classification suffers from the problem of insufficient data, and data augmentation is an effective method to alleviate this problem. However, the effect of conventional ...

The lower the uncertainty in solar resource data, the lower the investment costs. IEA PVPS Task 16 has organized and published two benchmarks to make uncertainty of models and data comparable – a ...