Introduction to Deep Learning · HIT

Week 9   Part III · Architectures & Representation Learning

Convolutional Networks II

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.

Course
Stanford CS231n: Deep Learning for Computer Vision (Architectures) cs231n.github.io

The CNN course whose architecture module surveys AlexNet, VGG, GoogLeNet, and ResNet.

Book
Dive into Deep Learning, Chapter 8: Modern Convolutional Neural Networks d2l.ai

Dedicated sections on batch normalization and residual networks plus other modern architectures.

Video
CS231n Lecture 9: CNN Architectures youtube.com

Canonical lecture on ResNet and the residual-connection idea that lets very deep nets train.

Blog / Docs
Dive into Deep Learning, 8.6 Residual Networks (ResNet) d2l.ai

A self-contained explainer of residual blocks with a ResNet-18 implementation in PyTorch.

← Back to the Week 9 lab

PreviousWeek 8: Convolutional Networks INextWeek 10: Recurrent Networks (RNNs)