Fig. 2From: Comparing the performance of time series models with or without meteorological factors in predicting incident pulmonary tuberculosis in eastern ChinaThe recurrent neural network (RNN). a The structure diagram of the RNN; b The unfolding diagram of the forward propagation of the RNN. \({X}_{t}\): input at time \(t\); \({h}_{t}\): hidden state at time \(t\); \({y}_{t}\): output at time \(t\); \(W\): weight of the input; \(U\): weight of the input at the moment; \(V\): weight of the outputBack to article page