27 citations · 48 across the 20 of their papers we have counts for
Showing 2017Show all
2 papers · 1 filter
stat.ML2017★ 3 cited
Differentially Private Variational Dropout
Beyza Ermis, Ali Taylan Cemgil
Deep neural networks with their large number of parameters are highly flexible learning systems. The high flexibility in such networks brings with some serious problems such as ove…
stat.ML2017★ 3 cited
Differentially Private Dropout
Beyza Ermis, Ali Taylan Cemgil
Large data collections required for the training of neural networks often contain sensitive information such as the medical histories of patients, and the privacy of the training d…