// ⬡ Deep Learning Foundations
Residual Networks (ResNet)
Skip connections let signals bypass layers, making very deep nets trainable.
残差网络 2015 Foundational core
IN PLAIN WORDS
Each block learns a residual: output = input + F(input), so gradients flow through the shortcut. Depth jumped to 100+ layers; every Transformer sublayer uses it.
Used in: Vision backbones; residual paths in Transformers
TIMELINE · prerequisites → this → what builds on it
01Original paper
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren, et al. · 2015
arXiv ↗ ✓ Verified · arXiv API
02Where it sits
Learn the left column first; the right column builds on this one.
Then you can learn
Left: prerequisites · right: builds on this · dashed: related. Full map →
03Learning resources
Official docs, explainers, courses and reference code. All links checked.
04Where the course teaches it
On learning paths:Zero to Deep Learning
For AI / data
- Verification: verified, checked 2026-10-21.
- JSON: /api/learn/algorithms.json (id:
resnet)