no code implementations • 21 Dec 2023 • Aaron Maiwald, Leon Ackermann, Maximilian Kalcher, Daniel J. Wu
We find that, while the choice of representation entails a choice within the tradeoff between bias and variance, certain representations are practically more effective in highlighting features which increase the signal-to-noise ratio of the data.
no code implementations • 20 Jun 2022 • Yang A. Chuming, Daniel J. Wu, Ken Hong
Recent advances in deep learning have enabled realistic digital alterations to videos, known as deepfakes.
no code implementations • CVPR 2021 • Zelun Luo, Daniel J. Wu, Ehsan Adeli, Li Fei-Fei
We propose a novel method for privacy-preserving training of deep neural networks leveraging public, out-domain data.
1 code implementation • 30 Mar 2021 • Daniel J. Wu, Avoy Datta
We propose a simple method by which to choose sample weights for problems with highly imbalanced or skewed traits.
no code implementations • 30 Mar 2021 • Daniel J. Wu, Avoy Datta, Vinay Prabhu
User authentication through gait analysis is a promising application of discriminative neural networks -- particularly due to the ubiquity of the primary sources of gait accelerometry, in-pocket cellphones.