Week 9 Part III · Architectures & Representation Learning
Batch and layer normalization; residual connections; modern CNN design.
Curated, free, canonical references for this week: a course or lecture, a book chapter, a video, and an authoritative blog post or official tutorial. Each opens in a new tab.
The CNN course whose architecture module surveys AlexNet, VGG, GoogLeNet, and ResNet.
Dedicated sections on batch normalization and residual networks plus other modern architectures.
Canonical lecture on ResNet and the residual-connection idea that lets very deep nets train.
A self-contained explainer of residual blocks with a ResNet-18 implementation in PyTorch.