Uncertainty-based knowledge distillation for Bayesian deep neural network compression

DOI10.1016/J.IJAR.2024.109301MaRDI QIDQ7036253zbMATH OpenFDO

Authors Mina Hemmatian, Ali Shahzadi, Saeed Mozaffari

Publication date 28 January 2025

Published in International Journal of Approximate Reasoning (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.IJAR.2024.109301

zbMATH Keywords

aleatoric uncertaintyBayesian deep neural networkscontribution factorepistemic uncertaintyknowledge distillation-based methodstemperature parameter

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Reasoning under uncertainty in the context of artificial intelligence (68T37)

Cites work

• A novel approach to discretizing information systems associated with neighborhood rough sets
• Aleatoric and epistemic uncertainty in machine learning: an introduction to concepts and methods
• Belief functions and rough sets: survey and new insights
• Deep evidential fusion network for medical image classification
• Making inferences in incomplete Bayesian networks: a Dempster-Shafer belief function approach
• Mixed aleatory and epistemic uncertainty quantification using fuzzy set theory
• Pattern recognition and machine learning.
• Possibility theory and statistical reasoning
• Scaling up Bayesian variational inference using distributed computing clusters
• Uncertainty quantification in logistic regression using random fuzzy sets and belief functions
• Uncertainty quantification using Bayesian neural networks in classification: application to biomedical image segmentation

This page was built for publication: Uncertainty-based knowledge distillation for Bayesian deep neural network compression

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7036253)