Unsupervised learning means learning by observation, not by example. This type of learning works with unlabeled data. Dimensionality reduction and clustering are examples of such learning. Dimensionality reduction is used to reduce a large number of attributes to just a few that can produce the same results. There are several methods that are available for reducing the dimensionality of data, such as principal component analysis (PCA), t-SNE, wavelet transformation, and attribute subset selection.
The term cluster means a group of similar items that are closely related to each other. Clustering is an approach for generating units or groups of items that are similar to each other. This similarity is computed based on certain features or characteristics of items. We can say that a cluster is a set of data points that are similar to others in its cluster and dissimilar to data points of other clusters. Clustering has numerous applications, such as in searching documents...
