Start here
Your plan
| Days | Module | Slides |
|---|---|---|
| 1 | Convolutions: edges, padding and strides | C4 week 1 |
| 2 | Convolution layers, pooling, and why convolutions | C4 week 1 |
| 3 | Classic networks, ResNets, 1×1 convolutions and Inception | C4 week 2 |
| 4 | MobileNet, EfficientNet and practical advice | C4 week 2 |
| 5 | Object detection: localization, YOLO, IoU and NMS | C4 week 3 |
| 6 | Region proposals and segmentation with U-Net | C4 week 3 |
| 7 | Face recognition | C4 week 4 |
| 8 | Neural style transfer, and 1D and 3D convolutions | C4 week 4 |
| 9 | Build it, and interview drill | notebooks |
About 1 to 1.5 hours a day, for 9 days.
Code in this course is written for PyTorch 2.15 (October 2026), TensorFlow 2.21 and Keras 3.15. The slides use TensorFlow 1-style code in places; the notes show the current way.
How each lesson works: the slides for that part open at the top of the lesson. Read them, then the notes under them: the notes explain what the slide skips, show today's PyTorch and Keras code, and point to the experiments in the notebook. Notebooks are files that come with the course: open them in Google Colab (free, nothing to install), download them for Jupyter or VS Code, or read their PDF versions with all the outputs.
This is part 4 of 5: Convolutional neural networks, with notes on what came after the slides (vision transformers, modern detectors, segmentation models).
Credit: the slides are from the Deep Learning Specialization (course 4, Convolutional Neural Networks) by DeepLearning.AI, taught by Andrew Ng, shared under Creative Commons BY-SA 2.0 for non-commercial educational use. Take the full course on Coursera for the videos and graded labs.
Maths is written in plain text: W·x is a matrix product, Σ a sum, ^ a power, [l] the layer, (i) the example.