📄️ Table of contents
Free discovery course on computer vision in 6 lessons. What a computer actually sees in an image, how convolution finds patterns, the four vision tasks, why transformers arrived, and where vision still fails.
📄️ 1. What a computer sees
Lesson 1 of the free computer vision course: images as grids of numbers, colour channels, resolution trade-offs, and why the same object produces completely different pixel values.
📄️ 2. Convolution
Lesson 2 of the free computer vision course: what a convolutional filter does, why weight sharing matters, how layers build a hierarchy of features, and why transfer learning means you need far less data.
📄️ 3. The four tasks
Lesson 3 of the free computer vision course: what each vision task returns, what it costs to annotate, which metrics matter, and how to choose the cheapest task that solves your problem.
📄️ 4. Modern architectures
Lesson 4 of the free computer vision course: the architectural line from AlexNet through ResNet to vision transformers and foundation models, and how to choose between them.
📄️ 5. Where it still fails
Lesson 5 of the free computer vision course: why models that test well fail in production, what shortcut learning is, how adversarial examples work, and how biased datasets produce harmful systems.
📄️ 6. Recap and FAQ
Lesson 6 of the free computer vision course: a synthesis of the five lessons, a practical decision guide for vision projects, and twelve frequently asked questions answered directly.
📄️ 7. Quiz and attestation
Test your understanding of computer vision with a free 5-question quiz, corrected and explained: classification versus detection versus segmentation, annotation cost, augmentation and real deployment constraints.