A Nearest neighbor search locates the k-nearest neighbors or all neighbors within a specified distance to query data points, based on the specified distance metric. Available distance metrics include Euclidean, Hamming, and Mahalanobis, among others.

Statistics and Machine Learning Toolbox™ offers two ways to find nearest neighbors. You can create a searcher object with a training data set, and pass the object and query data sets to the object functions (knnsearch and rangesearch). Or, you can use the knnsearch and rangesearch functions, which take both a training data set and a query data set directly. Creating a searcher object is preferable when you have multiple query data sets because the searcher object stores information common to the data sets. For example, a KDTreeSearcher object stores a Kd-tree.