Post-Cutoff.com
  1. Home
  2. Timeline
  3. 2015
  4. ResNet: residual learning enables very deep networks

ResNet: residual learning enables very deep networks

★★★★researchMicrosoft Researchconfidence: high

Kaiming He and colleagues introduced residual connections, allowing networks with 152+ layers to train; ResNet won ILSVRC-2015 with 3.57% top-5 error.

Key facts

What happened

Residual blocks learn a correction to an identity mapping, making optimization of very deep networks tractable.

Why it matters

Residual connections are a universal ingredient of deep learning; every Transformer block uses them.

Changelog

  • 2026-09-29: created

Related events

  1. AlexNet wins ImageNet challenge, igniting the deep learning boom ★★★★★
  2. 'Attention Is All You Need' introduces the Transformer ★★★★★

Sources (2)

id: 2015-12-10-resnet · updated 2026-09-29 · open in the interactive timeline