# On an Interpretation of ResNets via Solution Constructions

**Authors:** Changcun Huang  
**arXiv:** [2212.05663](https://arxiv.org/abs/2212.05663)  
**Date:** 2022-12-12  
**Summary page:** https://www.summarizepaper.com/en/paper/2212.05663v2/

## Abstract

This paper first constructs a typical solution of ResNets for multi-category classifications by the principle of gate-network controls and deep-layer classifications, from which a general interpretation of the ResNet architecture is given and the performance mechanism is explained. We then use more solutions to further demonstrate the generality of that interpretation. The universal-approximation capability of ResNets is proved.