no code implementations • 12 Apr 2022 • Mohit Kumar, Weiping Zhang, Lukas Fischer, Bernhard Freudenthaler
This study leverages the data representation capability of fuzzy based membership-mappings for practical secure distributed deep learning using fully homomorphic encryption.
no code implementations • 25 Apr 2021 • Shurui Li, Jianqin Xu, Jing Qian, Weiping Zhang
Deep learning, accounting for the use of an elaborate neural network, has recently been developed as an efficient and powerful tool to solve diverse problems in physics and other sciences.
no code implementations • 7 Nov 2018 • Ye Tian, Weiping Zhang
In this paper, we propose an effective THresholding method based on ORder Statistic, called THORS, to convert an arbitrary scoring-type classifier, which can induce a continuous cumulative distribution function of the score, into a cost-sensitive one.