Fig 4. The structure of the forward RNN for each observed variant with residual connections for the case of four stacked RNN cells.

${\mathit{x}}_{v_i}$ and ${\mathit{x}}_{v_{i+1}}$ are input feature vectors for observed variants v_i and v_i+1, respectively. ${\mathit{s}}_{i,j}^{\left(f\right)}$ is the state of the RNN cell of the jth layer for observed variant v_i and used as the input of the state for the RNN cell of the jth layer for observed variant v_i+1. Circles with + represent the addition of tensors for residual connections. The output of the RNN cell of the top layer, o_i,4, is handled as the output of RNN for each observed variant.