Visualizing Classification Structure in Deep Neural Networks

07/12/2020
by   Bilal Alsallakh, et al.
0

We propose a measure to compute class similarity in large-scale classification based on prediction scores. Such measure has not been formally pro-posed in the literature. We show how visualizing the class similarity matrix can reveal hierarchical structures and relationships that govern the classes. Through examples with various classifiers, we demonstrate how such structures can help in analyzing the classification behavior and in inferring potential corner cases. The source code for one example is available as a notebook at https://github.com/bilalsal/blocks

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset