Title
Alpha-divergence minimization with mixed variational posterior for Bayesian neural networks and its robustness against adversarial examples
Abstract
•We develop alpha-divergence minimization with mixed variational posterior.•The proposed method is time-efficient and extendable to various neural networks.•We provide the uncertainty comparison of Bayesian neural networks adopting different posterior approximations.•Experimental results show that our method achieves higher performance.
Year
DOI
Venue
2021
10.1016/j.neucom.2020.10.087
Neurocomputing
Keywords
DocType
Volume
Bayesian neural networks,Alpha divergence,Approximate inference
Journal
423
ISSN
Citations 
PageRank 
0925-2312
1
0.39
References 
Authors
0
2
Name
Order
Citations
PageRank
ying liu136446.92
Shiliang Sun21732115.55