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

Hengyu Fu Tianyu Guo Yu Bai Song Mei

Published in: NeurIPS (2023)

Keyphrases

experimental study
machine learning
website
statistical analysis
empirical studies
prior knowledge
image features
multi layer
database
structural information
false positives
benchmark datasets
feature vectors
information technology
feature space
feature extraction
feature selection
computer vision
learning algorithm