Tag: #ResNet
Kubernetes, DevOps and MLOps, written from things we ran and measured ourselves · 1 posts
ResNet: Why Residual Connections Made Deep Networks Trainable and Batch Normalization
We examine how ResNet solved the "degradation paradox" where stacking more layers actually increases training error. If a block learns only the "residual to add to the input" rather than the entire output, the gradient f
2026-10-17 · 13 min read #비전 모델#ResNet#잔차 연결#배치 정규화#기울기 소실