c460dc0f18fc309ac07306a4a55d2fd6-Paper.pdf

However,twokeydrawbacks of RPS-l2 are thatthey(i)leadtodisagreement between theoriginally trained networkandthe RPS-l2 regularized network modification and (ii) often yield a static ranking of training data fortest points inthesame class, independent ofthetest point being classified. Inspired by the RPS-l2 approach, we propose an alternative method based on a local Jacobian Taylor expansion (LJE).