Sharing Attention Weights for Fast Transformer.

Tong Xiao Yinqiao Li Jingbo Zhu Zhengtao Yu Tongran Liu

Published in: IJCAI (2019)

Keyphrases

linear combination
fault diagnosis
weighted sum
relative importance
pairwise comparison
fuzzy logic
data sets
weighted average
visual attention
data sharing
optimal weights
distribution network
weighting scheme
artificial neural networks
search algorithm
decision making
neural network