A study companion for Andrew Ng’s deep learning courses

What it does

This repository collects markdown summaries and Jupyter notebooks that follow Andrew Ng’s Coursera Deep Learning Specialization and his classic Machine Learning course. The material is organized by course and week, covering neural network basics through convolutional and sequence models, with links to lecture playlists and relevant research papers.

The interesting bit

It is essentially a curated study guide rather than a standalone framework. The value lies in having condensed notes, executable coursework notebooks, and paper references—like AlexNet, YOLO, and FaceNet—all indexed in one place instead of scattered across Coursera tabs and arXiv bookmarks.

Key highlights

• Covers five core deep learning topics, from basic neural networks to CNNs and sequence models.
• Includes Jupyter notebooks for weekly exercises such as logistic regression, ResNets, and neural style transfer.
• Links to foundational papers alongside the practical notebooks.
• Offers a single consolidated PDF of the deep learning specialization notes.
• Also houses notebooks for the older Machine Learning course.

Caveats

• The README is mostly a table of contents with generic GIFs; it does not explain how the notes differ from the course lectures.
• Some weekly notebook links appear duplicated or point to mismatched folders (for example, Week 2 and Week 3 of the neural-network section both link to the same logistic-regression notebook).
• All code is coursework-derived, so do not expect original libraries or production-grade implementations.

Verdict Grab this if you are currently taking Andrew Ng’s courses and want a secondary reference with quick notebook access. Skip it if you are looking for novel frameworks or advanced implementations beyond introductory coursework.