On Performance and Calibration of Natural Gradient Langevin Dynamics

Producing deep neural network (DNN) models with calibrated confidence is essential for applications in many fields, such as medical image analysis, natural language processing, and robotics. Modern neural networks have been reported to be poorly calibrated compared with those from a decade ago. The...

詳細記述

書誌詳細
主要な著者: Hanif Amal Robbani, Alhadi Bustamam, Risman Adnan, Shandar Ahmad
フォーマット: 論文
言語:English
出版事項: IEEE 2023-01-01
シリーズ:IEEE Access
主題:
オンライン・アクセス:https://ieeexplore.ieee.org/document/10131934/

類似資料