The restricted Boltzmann machine (RBM) is a fundamentally different model from the feed-forward network. Conventional neural networks are input-output mapping networks where a set of inputs is mapped to a set of outputs. On the other hand, RBMs are networks in which the probabilistic states of a network are learned for a set of inputs, which is useful for unsupervised modeling.
Aggarwal, C. C. (2018). Restricted Boltzmann Machines. In Neural Networks and Deep Learning (pp. 235–270). Springer International Publishing. https://doi.org/10.1007/978-3-319-94463-0_6