← Search

Shih-Han Chan

2 accepted papers

2024

Explaining Generalization Power of a DNN Using Interactive Concepts

AAAI 2024technical

This paper explains the generalization power of a deep neural network (DNN) from the perspective of interactions. Although there is no universally accepted definition of the concepts encoded by a DNN, the sparsity of interactions in a DNN has been proved, i.e., the output score of a DNN can be well…

Cited by 18SourcePDFScholar
2022

Towards Theoretical Analysis of Transformation Complexity of ReLU DNNs

ICML 2022spotlight

This paper aims to theoretically analyze the complexity of feature transformations encoded in piecewise linear DNNs with ReLU layers. We propose metrics to measure three types of complexities of transformations based on the information theory. We further discover and prove the strong correlation bet…