all AI news
On Deep Neural Network Calibration by Regularization and its Impact on Refinement. (arXiv:2106.09385v3 [cs.LG] UPDATED)
cs.LG updates on arXiv.org arxiv.org
Deep neural networks have been shown to be highly miscalibrated. often they
tend to be overconfident in their predictions. It poses a significant challenge
for safety-critical systems to utilise deep neural networks (DNNs), reliably.
Many recently proposed approaches to mitigate this have demonstrated
substantial progress in improving DNN calibration. However, they hardly touch
upon refinement, which historically has been an essential aspect of
calibration. Refinement indicates separability of a network's correct and
incorrect predictions. This paper presents a theoretically and …
arxiv deep neural network impact network neural network regularization