no code implementations • 11 Feb 2020 • Rahul Soni, Naresh Shah, Jimmy D. Moore
Our method sits on top of a given Neural Network, requires a single scan of training data to estimate class distribution statistics, and is highly scalable to deep networks and wider pre-softmax layer.
no code implementations • 10 Feb 2020 • Rahul Soni, Naresh Shah, Chua Tat Seng, Jimmy D. Moore
For robustness, we define it as the ability of an intermediate layer to be consistent in its recall rate (the effectiveness) for different random seeds.