Skip to main content
. 2019 Dec 16;116(52):26414–26420. doi: 10.1073/pnas.1911815116

Fig. 2.

Fig. 2.

Variation of RNN architecture to encapsulate temporal and nontemporal inputs: postmixing nontemporal data through a dense network (A), configuring nontemporal data as initial hidden-state value through a dense network (B), or establishing a secondary nontemporal hidden state in GRU formulation (C).