Variational mean-field theory for training restricted Boltzmann machines with binary synapses
Variational mean-field theory for training restricted Boltzmann machines with binary synapses is a scholarly work, published in 2020 in ''Physical Review E''. The main subjects of the publication include restricted Boltzmann machine, maximization, Boltzmann machine, binary numeral system, computer science, artificial intelligence, unsupervised learning, gradient descent, memristor, artificial neural network, obstacle, mathematics, and field. The authors propose a variational mean-field theory in which the distribution of synaptic weights is considered.