This document provides an introduction to machine learning concepts. It defines machine learning as allowing computers to learn without being explicitly programmed. Two main types are described: supervised learning, where the goal is to predict known outputs from inputs, and unsupervised learning, where patterns in unknown data are identified. Supervised learning is further divided into classification and regression problems. Example algorithms covered include k-nearest neighbors, decision trees, and linear regression. Key concepts like bias, variance, and dimensionality are also introduced.