发明申请
US20170032035A1 Representation Learning Using Multi-Task Deep Neural Networks
审中-公开
使用多任务深层神经网络的表征学习
- 专利标题： Representation Learning Using Multi-Task Deep Neural Networks
- 专利标题（中）： 使用多任务深层神经网络的表征学习
-
申请号： US14811808申请日： 2015-07-28
-
公开(公告)号： US20170032035A1公开(公告)日： 2017-02-02
- 发明人: Jianfeng Gao , Li Deng , Xiaodong He , Ye-Yi Wang , Kevin Duh , Xiaodong Liu
- 申请人： Microsoft Technology Licensing, LLC
- 主分类号： G06F17/30
- IPC分类号： G06F17/30 ; G06N3/08
摘要：
A system may comprise one or more processors and memory storing instructions that, when executed by one or more processors, configure one or more processors to perform a number of operations or tasks, such as receiving a query or a document, and mapping the query or the document into a lower dimensional representation by performing at least one operational layer that shares at least two disparate tasks.
公开/授权文献
信息查询
