Module 13: Convolutional Neural Networks

Deep learning for images. This module builds convolutional networks from the convolution operation up, and trains real image classifiers in PyTorch.

What You’ll Learn¶

• The convolution operation: filters, padding, stride, and feature maps

• Pooling, weight sharing, and why CNNs suit spatial data

• CNN architectures: stacking conv/pool/fully-connected layers

• Regularization with dropout and data augmentation

• Training an image classifier in PyTorch end-to-end

Lecture Materials¶

• 📊 Lecture Slides (PDF)

• 📓 Chapter notebook: Classifying Images with Deep Convolutional Neural Networks

Prerequisites¶

• Modules 10–11

Reference¶

Raschka & Mirjalili, Machine Learning with PyTorch and Scikit-Learn, Chapter 14.