Sharing Attention Weights for Fast Transformer.

Tong Xiao Yinqiao Li Jingbo Zhu Zhengtao Yu Tongran Liu

Published in: CoRR (2019)

Keyphrases

linear combination
fuzzy logic
weighted sum
visual attention
data sets
high voltage
relative importance
information sharing
linearly combined
optimal weights
weighted average
weighting scheme
knowledge sharing
multi agent
website
artificial intelligence
learning algorithm
data mining
neural network