Measuring Representational Robustness of Neural Networks Through Shared Invariances

Vedant Nanda, Till Speicher, Camila Kolling, John P. Dickerson, Krishna P. Gummadi, Adrian Weller

Abstract: A major challenge in studying robustness in deep learning is defining the set of “meaningless” perturbations to which a given Neural Network (NN) should be invariant. Most work on robustness implic...