65 citations · 75 across the 4 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
A Comparative Study of Label-free Representation Quality Metrics in Deep Learning
Daniel Richards Arputharaj, Daniel Jönsson, Gabriel Eilertsen
We present a comparative study of label-free metrics for assessing the quality of representations in deep neural networks to understand their reliability under a wide variety of co…
cs.LG2022★ 4 cited
Neural Activation Patterns (NAPs): Visual Explainability of Learned Concepts
Alex Bäuerle, Daniel Jönsson, Timo Ropinski
A key to deciphering the inner workings of neural networks is understanding what a model has learned. Promising methods for discovering learned features are based on analyzing acti…