On an Interpretation of ResNets via Solution Constructions
Not on the map. Why?
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 9 of its 16 references that are in the map. First posted on arXiv 12 Dec 2022.
Builds on
9 of 16 references.
References · 9
- 2017Attention Is All You Needcited by 59,932
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2018Neural Ordinary Differential Equationscited by 3,733
- 2016Identity Mappings in Deep Residual Networkscited by 1,960
- 2015Highway Networkscited by 257
- 2018ResNet with one-neuron hidden layers is a Universal Approximatorcited by 78
- 2022Theoretical Exploration of Solutions of Feedforward ReLU Networkscited by 4
- 2022On a Mechanism Framework of Autoencoderscited by 3
- 2022Universal Solutions of Feedforward ReLU Networks for Interpolationscited by 1
Built on by
Not cited yet.