Qu'est-ce que « Causal convolution, temporal convolutional network » ?

A causal convolution uses only the current and earlier positions: $u_t = \sum_{j=0}^{k-1}B_jz_{t - jr}$, with dilation $r$. A temporal convolutional network (TCN) stacks causal convolutions with dilations $1, 2, 4,\dots$, so that the receptive field grows exponentially with depth, usually with residual connections (Bai, Kolter and Koltun, 2018).