Apr 12, 2024 · We measure the Out-of-domain uncertainty in the prediction of Neural Networks using a statistical notion called Lens Depth (LD) combined with Fermat Distance.

We measure the Out-of-domain uncertainty in the prediction of Neural Networks using a statistical notion called ``Lens Depth'' (LD) combined with Fermat ...

Apr 12, 2024 · We measure the Out-of-domain uncertainty in the prediction of Neural Networks using a statistical notion called “Lens Depth” (LD) combined with Fermat Distance.

We measure the Out-of-domain uncertainty in the prediction of Neural Networks using a statistical notion called ``Lens Depth'' (LD) combined with Fermat

Apr 14, 2024 · This paper presents a novel approach for uncertainty quantification by combining statistical depth and Fermat distance. · The proposed method ...

Apr 12, 2024 · Combining Statistical Depth and Fermat Distance for Uncertainty Quantification. The method is applicable to any classification model as it is ...

Combining Statistical Depth and Fermat Distance for Uncertainty Quantification ... The method is applicable to any classification model as it is applied directly ...

Jun 25, 2024 · Combining Statistical Depth and Fermat Distance for Uncertainty Quantification. CoRR abs/2404.08476 (2024). [i1]. view. electronic edition via ...

本论文旨在使用“Lens Depth”（LD）和Fermat Distance的组合来测量神经网络预测中的域外不确定性，以捕捉特征空间中点相对于分布的“深度”，并且不需要对分布形式做出任何假设。

Apr 12, 2024 · Figure 1 for Combining Statistical Depth and Fermat Distance for Uncertainty Quantification. Abstract:We measure the Out-of-domain uncertainty ...