# On an Interpretation of ResNets via Solution Constructions

arXiv: https://arxiv.org/abs/2212.05663 · HTML: https://mlsanity.com/paper/2212.05663/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 16 references that are in the map.
- First posted on arXiv 12 Dec 2022.

## Builds on (most cited first, 9 of 9)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Neural Ordinary Differential Equations](https://mlsanity.com/paper/1806.07366/) (2018)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [Highway Networks](https://mlsanity.com/paper/1505.00387/) (2015)
- [ResNet with one-neuron hidden layers is a Universal Approximator](https://mlsanity.com/paper/1806.10909/) (2018)
- [Theoretical Exploration of Solutions of Feedforward ReLU Networks](https://mlsanity.com/paper/2202.01919/) (2022)
- [On a Mechanism Framework of Autoencoders](https://mlsanity.com/paper/2208.06995/) (2022)
- [Universal Solutions of Feedforward ReLU Networks for Interpolations](https://mlsanity.com/paper/2208.07498/) (2022)

## Abstract (arXiv)

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.