Harish G. Ramaswamy

On the Learning Dynamics of Attention Networks
On the Interpretability of Attention Networks
Ablation-CAM: Making AI trustworthy
Inductive Bias of Gradient Descent for Exponentially Weight Normalized Smooth Homogeneous Neural Nets
Ablation-CAM: Visual Explanations for Deep Convolutional Network via Gradient-free Localization
On Knowledge Distillation From Complex Networks