Fig. 4
From: Efficient representation of quantum many-body states with deep neural networks
Representation of tensor network states with DBMs. a Illustration of a tensor network state. b Representation of this tensor network state by a DBM. Visible (hidden) neurons play the role of physical (bond) indices, respectively. Port neuron represents either the bond index for the next step of tensor contraction or the physical index if there is no further contraction. The gray box stands for the local tensor gadget \({A_{{x_1} \cdots {x_c}}}\) which can be efficiently represented with a DBM
