CNNs — LeNet to ResNet

Every major CNN of the last thirty years is the same conv–nonlinearity–downsample recipe with one new idea bolted on. Learn the ideas in order.

Learn + Build 1.3 hr Python

Prerequisites: Phase 3 Lesson 11 (PyTorch), Phase 4 Lesson 01 (Image Fundamentals), Phase 4 Lesson 02 (Convolutions from Scratch)

#Learning Objectives

Trace the architectural lineage LeNet-5 -> AlexNet -> VGG -> Inception -> ResNet and state the single new idea each family contributed
Implement LeNet-5, a VGG-style block, and a ResNet BasicBlock in PyTorch, each under 40 lines
Explain why residual connections turn a 1,000-layer network from untrainable into state-of-the-art
Read a modern backbone (ResNet-18, ResNet-50) and predict its output shape, receptive field, and parameter count before looking at the source

Full Access lesson

Unlock all 503 lessons, video, code, quizzes and every future update. Pay in your own currency with Paystack.

The text and code of this lesson are based on AI Engineering from Scratch by Rohit Ghumare, MIT licensed.