Table 4 All architectures (recurrent neural network (RNN), sub-sequenced input recurrent neural network (RNNseq), feedforward neural network (FNN), sub-sequenced input feedforward neural network (FNNseq), convolutional neural network (CNN)) are tested on a new motion from the separate subject and evaluated by the zero-line score Z_s, mean square error MSE, the squared correlation coefficient r², and the coefficient of determination R²

From: The concepts of muscle activity generation driven by upper limb kinematics