Search Results for author: Keji Shao

Found 1 papers, 0 papers with code

DropDim: A Regularization Method for Transformer Networks

no code implementations20 Apr 2023 Hao Zhang, Dan Qu, Keji Shao, Xukui Yang

In contrast to the general dropout method, which randomly drops neurons, DropDim drops part of the embedding dimensions.

Cannot find the paper you are looking for? You can Submit a new open access paper.