Causal convolutions are a type of convolution used for temporal data which ensures the model cannot violate the ordering in which we model the data: the prediction $p(x_{t+1} | x_{1}, \ldots, x_{t})$ emitted by the model at timestep $t$ cannot depend on any of the future timesteps $x_{t+1}, x_{t+2}, \ldots, x_{T}$. For images, the equivalent of a causal convolution is a masked convolution which can be implemented by constructing a mask tensor and doing an element-wise multiplication of this mask with the convolution kernel before applying it. For 1-D data such as audio one can more easily implement this by shifting the output of a normal convolution by a few timesteps.
Source: WaveNet: A Generative Model for Raw AudioPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Time Series Analysis | 4 | 10.81% |
Speech Recognition | 3 | 8.11% |
Time Series Forecasting | 3 | 8.11% |
Voice Conversion | 2 | 5.41% |
Traffic Prediction | 2 | 5.41% |
Denoising | 1 | 2.70% |
Density Estimation | 1 | 2.70% |
Sequential Image Classification | 1 | 2.70% |
Link Prediction | 1 | 2.70% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |