This video introduces the temporal convolutional network (TCN), a 1D convolutional neural network designed for sequence modeling tasks.
The outline of this lecture includes:
(1) Introduction about the motivation, central idea, and architecture overview of the TCN.
(2) 1D dilated convolution about the definition and padding rule of the convolution process in TCN.
(3) Residual block about the two main components in a residual block, dilated convolution layer, and residual shortcut and the setting of the residual block for achieving long memory.
Any comments are welcome. (email: powwhuang@gmail.com)
All resources are available on the website (quarter.tw)
Негізгі бет quarter CNN: Temporal Convolution Networks (TCN)
Пікірлер: 8