Neural Foundations · 2015
Deep Residual Learning for Image Recognition (ResNet)
Introduced residual learning with identity skip connections so layers fit a residual function rather than a full mapping, removing the degradation problem that made very deep networks harder to optimize and less accurate.
Editorial record
Plain-language summary
The authors added shortcut connections that add a layer block's input to its output, so each block only has to learn the difference from identity. This made gradients flow through very deep stacks and allowed networks of 50 to 152 layers to train and improve rather than degrade, winning ImageNet 2015. Residual blocks became a default component in most later deep vision and language architectures.
Knowledge graph
Relationships
Antecedents
Depends onEvidence: Direct
Attention Is All You Need
Residual sublayers (x + Sublayer(x)) in every block
P-001 Sec 3.1
Source record
Provenance
- Record ID
- A-009
- Record created
- 2026-07-13
- Last reviewed
- 2026-07-14
- Record version
- 2
- https://arxiv.org/abs/1512.03385
- arXiv:1512.03385
Citation caveat: Citation metadata is approximate and marked unverified in the source dataset.