Search Results for author:
Found 2 papers, 1 papers with code
FairCal: Fairness Calibration for Face Verification
However, they still have drawbacks: they reduce accuracy (AGENDA, PASS, FTC), or require retuning for different false positive rates (FSN).
Volume-preserving Neural Networks
We construct a new architecture for deep neural networks where all layers (except the output layer) of the network are a combination of rotation, permutation, diagonal, and activation sublayers which are all volume preserving.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
