Texonom
Texonom
/
Engineering
Engineering
/Data Engineering/Artificial Intelligence/Machine Learning/Neural Network/Neural Network Structure/Seq2Seq/Attention Mechanism/Attention Mechanism Optimization/
Clustered attention
Search

Clustered attention

Creator
Creator
Seonglae Cho
Created
Created
2023 Oct 6 7:29
Editor
Editor
Seonglae Cho
Edited
Edited
2024 Jan 17 14:57
Refs
Refs
Fast Transformers with Clustered Attention
Transformers have been proven a successful model for a variety of tasks in sequence modeling. However, computing the attention matrix, which is their key component, has quadratic complexity with...
Fast Transformers with Clustered Attention
https://arxiv.org/abs/2007.04825
Fast Transformers with Clustered Attention
 
 
 
 
 
 
 
 
 

Recommendations

Texonom
Texonom
/
Engineering
Engineering
/Data Engineering/Artificial Intelligence/Machine Learning/Neural Network/Neural Network Structure/Seq2Seq/Attention Mechanism/Attention Mechanism Optimization/
Clustered attention
Copyright Seonglae Cho