Fig. 6From: Efficiency of deep neural networks for joint angle modeling in digital gait assessmentArchitecture of a RNN with an input, a hidden, and an output layer. The network maps the input sequence \(\boldsymbol {x}_{D_{i},t}\) to a hidden sequence hn,t and to a sequence of outputs ym,t. The parameters Di, n, and m are the number of signals, the number of hidden units, and the number of outputs, respectively. Wxh, Whh, and Why are the input to hidden, hidden to hidden, and hidden to output matrices, respectively. The bias vectors of the network are represented by bh for the hidden layer and by by for the output layerBack to article page