Deep Computer Vision, CNN

Convolutional neural networks and modern vision systems, from pixels and tasks to hierarchical features and production constraints.

Updated 14 days ago

Deep Computer Vision: CNN

This track builds intuition for convolutional neural networks (CNNs) and how they power real computer vision systems: class labels, boxes, masks, depth, tracking, and more, often under noise, drift, and latency that benchmarks leave out.

Work through the lessons in order; each one sets up vocabulary and motivation for the next.

Course mapHover any lesson to see why it matters

Prerequisites

Deep Neural Networks

Stacking layers, backpropagation, activation functions, overfitting

Foundations of Regression

Logistic regression, loss functions, gradient descent

Lessons

01Beginner

The visual revolution

Deep learning ended decades of hand-crafted vision

02Beginner

Deep learning's role in computer vision

Learned features beat hand-crafted ones at every benchmark

03Beginner

From pixels to perception

Images are 3D tensors (H × W × C); models predict labels from them

04Intermediate

Feature detection & spatial hierarchy

Networks learn edges → textures → shapes → objects automatically

05Intermediate

Preserving spatial structure with CNNs

Convolutions respect locality; fully-connected layers discard it

06Intermediate

Filters, features & the power of convolutions

Slide a small learned filter across the image to detect one pattern

07Intermediate

Learning to see: CNN internals

Conv–ReLU–Pool stacks compress space while deepening channels

Unlocks

CNN Architectures (ResNet, EfficientNet)

Classic and modern networks that scale vision to ImageNet

Object Detection & Segmentation

Extend classification to localise and segment objects

Vision Transformers (ViT)

Apply attention to image patches as an alternative to convolutions

Test your understanding

Prof is ready

Prof will ask you questions about Deep Computer Vision, CNN — not explain it. You'll be surprised what you don't know until you have to say it.