A restricted Boltzmann machine (RBM) is a generative stochastic artificial neural network that learns a probability distribution over its set of inputs. It consists of two layers: a visible layer (representing input data) and a hidden layer (representing learned features), with connections only between the layers and not within each layer.

RBMs are used for unsupervised learning tasks such as dimensionality reduction, feature extraction, and pretraining deep networks. They are commonly employed in collaborative filtering, recommendation systems, and deep learning models.