This document discusses the k-nearest neighbors (kNN) machine learning algorithm. kNN is a non-parametric, lazy learning algorithm that is used for classification problems. It works by finding the k training examples that are closest in distance to the new data point, and predicting the class based on the majority class among those k neighbors. The key aspects of kNN are that it requires calculating distances between all examples to make predictions, and has no explicit training phase, unlike parametric methods.