Start here
Your plan
| Days | Module | Slides |
|---|---|---|
| 1 | Orthogonalization and setting up your goal | C3 week 1 |
| 2 | Train, dev and test distributions | C3 week 1 |
| 3 | Comparing to human-level performance | C3 week 1 |
| 4 | Error analysis and mismatched data | C3 week 2 |
| 5 | Transfer, multi-task and end-to-end learning | C3 week 2 |
| 6 | A real project, and interview drill | notebook |
About 1 hour a day, for 6 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 3 of 5: Structuring machine learning projects. No new network types: this is how to decide what to work on next, which is what separates fast teams from slow ones.
Credit: the slides are from the Deep Learning Specialization (course 3, Structuring Machine Learning Projects) 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.