📄️ What is Machine Learning?
Learning without being explicitly programmed — why the rule-based approach collapsed, what replaced it, why the idea only became practical recently, and how AI, ML and DL nest.
📄️ Applications and Major Techniques
The eight major machine learning techniques, the question each one answers, and how to read a real problem statement and work out which technique it is.
📄️ Types of Learning
Features and the numeric/categorical divide, the positive class, and the three learning paradigms — supervised, unsupervised and semi-supervised — separated by what your data actually contains.
📄️ Reinforcement Learning
The paradigm with no dataset — an agent learns by acting, receiving rewards and penalties, and the exploration-exploitation tradeoff that decides whether it finds the best policy or settles for a mediocre one.
📄️ The Toolkit and the Pipeline
The five Python libraries that do the work, how they stack, scikit-learn's fit/predict/transform contract, and the seven-step pipeline every project follows.