Fig. 6
From: Time series transformer for tourism demand forecasting
In the Self-Attention calculation of \(\:De{c}_{I5}\), \(\:De{c}_{I4}\) to \(\:De{c}_{I5}\) are attended, and decoder target masking prevents \(\:De{c}_{I6}\) to \(\:Toke{n}_{8}\) from being attended.
