Temporal Dropout

2000년 도입 · 논문 5편에서 사용

A method that randomly mask out all features coming from a specific time-step in time-series data. If the model used is independent of uneven sequences or missing data in time-series, like attention-based transformers, the masked time-steps can be just ignored in the forward prediction of the model. Otherwise, they have to be masked out with some numerical value.

출처: Crop Classification under Varying Cloud Cover with Neural Ordinary Differential Equations

소개 논문: Crop Classification under Varying Cloud Cover with Neural Ordinary Differential Equations