EasyDeepLearn

What is the key insight of ResNet's identity mapping?

medium

Answer

  • A residual block computes y = F(x) + x, where F is a stack of convolutions.
  • If the optimal function is close to identity, the block only needs to learn a small correction F(x) ≈ 0 — easier than learning the identity from scratch.
  • Enabled training 152-layer nets on ImageNet in 2015.
  • Skip connections also let gradients flow directly to earlier layers → no vanishing.
Check yourself — multiple choice
  • ResNet removes convolutions
  • y = F(x) + x — learn a correction to identity, easier to optimize, gradients flow via skip
  • ResNet is shallow
  • No skip connections

ResNet: learn residual F(x)=y-x → optimization easier, deep training enabled.

#architectures#computer-vision

Practise Deep Learning

214 interview questions in this topic.

Related questions