A Boltzmann machine is a stochastic recurrent neural network that can learn probability distributions over data. It is related to energy-based models and can be viewed as a generative counterpart to Hopfield networks with hidden units.
(Also stochastic Hopfield network with hidden units.) A type of stochastic recurrent neural network and Markov random field. Boltzmann machines can be seen as the stochastic, generative counterpart of Hopfield networks.