When I need to ramp on a technical domain, I like to build. To develop an intuition for why AI models work – and fail – the way they do, I worked through the courses below, from ML fundamentals to the underlying math and Python. My personal course notes are attached to give you a sense of what I learned and built.
Coursera/Andrew Ng – 3-part Machine Learning Specialization course
Coursera 1 – Supervised ML: Regression & Classification
Coursera 2 – Advanced Learning Algorithms
Coursera 3 – Unsupervised Learning, Recommenders, Reinforcement Learning
Khan Academy – especially Statistics and Probability
ARENA curriculum – working through their pre-requisites
ARENA Curriculum - Overall Notes
3Blue1Brown video series - for visual learners
Sample Video: https://youtu.be/WUvTyaaNkzM?si=_7vga4lQAl42kt1N
Google Kaggle coding Courses – e.g., Learning Python
Claude/ChatGPT are also useful coaches, in a pinch, though in my experience can struggle with debugging code – or lead you down winding paths. To help cement my learnings, and connect them to real-world use cases, I found an excellent coding and math tutor via Upwork (shout-out Andrew). Pro-Tip: reflect on and describe your preferred learning style, to find a coach that’s the right fit.