What can a Single Attention Layer Learn? A Study Through the Random Features Lens.

Hengyu Fu Tianyu Guo Yu Bai Song Mei

Published in: CoRR (2023)

Keyphrases

low level
feature set
empirical studies
data sets
information retrieval
information systems
feature selection
decision trees
classification accuracy
image classification
false positives
svm classifier
simulation study
salient features