Figure 3
From: Predicting quantum emitter fluctuations with time-series forecasting models
Unfolded sequential architecture in an RNN. \(X_t\) is the input at time step t, \(Y_t\) is the output at time step t and \(H_t\) is the hidden state at time t. The repeating modules are designed to act as a collective memory, sharing parameters across various time steps to store important data from earlier processing stages.
