Download
This repository outlines an ambitious self-study curriculum for learning machine learning in roughly three months, emphasizing breadth, momentum, and hands-on practice. It sequences core topics—math foundations, classic ML, deep learning, and applied projects—so learners can pace themselves week by week. The plan mixes reading, lectures, coding assignments, and small build-it-yourself projects to reinforce understanding through repetition and implementation. Because ML is a wide field, the curriculum favors pragmatic coverage over academic completeness, pointing learners to widely used tools and approachable resources. It’s intended to help beginners overcome decision paralysis by giving a concrete schedule and a minimal set of action-oriented tasks.
Features
- Week-by-week study roadmap covering math, ML, and deep learning
- Mix of lectures, readings, and coding tasks to balance theory and practice
- Project prompts that encourage building small, working ML demos
- Emphasis on widely used libraries and approachable resources
- Flexible pacing so learners can extend or compress modules as needed
- Acts as a checklist and accountability aid for self-studying
Project Samples
