Collected sources and patterns will appear here. Add from search or the patterns library.
HiddenState -> DistributionParameters
Project the final hidden state of a model to the parameters of a continuous probability distribution to enable sampling-based forecasting.
Problem it solves
Point forecasting fails to represent the inherent uncertainty and confidence intervals of future time-series trajectories.
Consumes
Emits
The real projects this mechanism was found in. Attribution is the point — this is how the best teams actually do it.