Supplementary Table 3 – Modelling individual variation in human walking gait across populations and walking conditions via gait recognition

Additional details of the convolutional transformer neural network architectures applied for gait recognition. N = number of samples. Transformer encoder layer hyper-parameter settings: d_model = number of input features (varied), nhead = 4, activation = 'gelu', and dim_feedforward = number of output features (varied).