Instance-wise Linearization of Neural Network for Model Interpretation

no code implementations • 25 Oct 2023 • Zhimin Li, Shusen Liu, Kailkhura Bhavya, Timo Bremer, Valerio Pascucci

For a neural network model, the non-linear behavior is often caused by non-linear activation units of a model.

Dimensionality Reduction

"Understanding Robustness Lottery": A Geometric Visual Comparative Analysis of Neural Network Pruning Approaches

no code implementations • 16 Jun 2022 • Zhimin Li, Shusen Liu, Xin Yu, Kailkhura Bhavya, Jie Cao, Diffenderfer James Daniel, Peer-Timo Bremer, Valerio Pascucci

We decomposed and evaluated a set of critical geometric concepts from the common adopted classification loss, and used them to design a visualization system to compare and highlight the impact of pruning on model performance and feature representation.

Network Pruning