Machine learning is a subset of artificial intelligence focused on building systems that learn patterns from data and improve their performance without explicit programming. At its core, the field revolves around three learning paradigms—supervised, unsupervised, and reinforcement learning—each addressing different types of problems. Understanding the fundamentals means grasping the bias-variance tradeoff: simpler models underfit (high bias), complex models overfit (high variance), and the goal is finding the sweet spot where a model generalizes well to unseen data while capturing the underlying signal.