BriefGPT.xyz
Aug, 2017
深度非对称多任务特征学习
Deep Asymmetric Multi-task Feature Learning
HTML
PDF
Haebeom Lee, Eunho Yang, Sung Ju Hwang
TL;DR
提出了Deep-AMTFL模型，可以通过使用不对称自编码器技术，在多任务学习中有效地学习共享的深度表示，同时有效地防止在特征共享过程中可能发生的负迁移。
Abstract
We propose Deep Asymmetric Multitask Feature Learning (
deep-amtfl
) which can learn deep representations shared across multiple tasks while effectively preventing
negative transfer
that may happen in the feature s
→