Fokoué, E. (2026). Multi-Head Attention as Ensemble Nadaraya-Watson Estimation: Variance Reduction, Decorrelation, and Optimal Head Diversity.
Chicago-Zitierstil (17. Ausg.)Fokoué, Ernest. Multi-Head Attention as Ensemble Nadaraya-Watson Estimation: Variance Reduction, Decorrelation, and Optimal Head Diversity. 2026.
MLA-Zitierstil (9. Ausg.)Fokoué, Ernest. Multi-Head Attention as Ensemble Nadaraya-Watson Estimation: Variance Reduction, Decorrelation, and Optimal Head Diversity. 2026.
Achtung: Diese Zitate sind unter Umständen nicht zu 100% korrekt.