Кластеризация

Grouping related examples, particularly during unsupervised learning. Once all the examples are grouped, a human can optionally supply meaning to each cluster. Many clustering algorithms exist. For example, the k-means algorithm clusters examples based on their proximity to a centroid, as in the following diagram: !A two-dimensional graph in which the x-axis is labeled tree width, and the y-axis is labeled tree height. The graph contains two centroids and several dozen data points. The data points are categorized based on their proximity. That is, the data points closest to one centroid are categorized as cluster 1, while those closest to the other centroid are categorized as cluster 2. A human researcher could then review the clusters and, for example, label cluster 1 as "dwarf trees" and cluster 2 as "full-size trees." As another example, consider a clustering algorithm based on an example's distance from a center point, illustrated as follows: !Dozens of data points are arranged in concentric circles, almost like holes around the center of a dart board. The innermost ring of data points is categorized as cluster 1, the middle ring is categorized as cluster 2, and the outermost ring as cluster 3. See the Clustering course for more information.

In the context of generative AI, clustering is an unsupervised machine learning technique used to group similar data points together based on their characteristics. This is achieved by defining a similarity measure (or metric) to compare data points, and grouping those with high similarity into the same cluster. In generative AI applications, this might involve clustering embeddings (numerical representations of text, images, or other data) to perform tasks like search, classification, or outlier detection. For example, customer segmentation can be achieved by clustering customer data to identify groups with similar behaviors or characteristics. For more information, see What is clustering?.