| 发明名称 |
Representation Learning Using Multi-Task Deep Neural Networks |
| 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. |
| 申请公布号 |
US2017032035(A1) |
申请公布日期 |
2017.02.02 |
| 申请号 |
US201514811808 |
申请日期 |
2015.07.28 |
| 申请人 |
Microsoft Technology Licensing, LLC |
发明人 |
Gao Jianfeng;Deng Li;He Xiaodong;Wang Ye-Yi;Duh Kevin;Liu Xiaodong |
| 分类号 |
G06F17/30;G06N3/08 |
主分类号 |
G06F17/30 |
| 代理机构 |
|
代理人 |
|
| 主权项 |
1. A system comprising:
one or more processors; and memory storing instructions that, when executed by the one or more processors, configure the one or more processors to perform operations comprising:
receiving a query or a document;mapping the query or the document into a lower dimensional representation by using at least one operational layer that shares operations of at least two disparate tasks, wherein the at least one operational layer is based, at least in part, on a multi-task deep neural network (DNN); andusing the lower dimensional representation to perform at least one of the at least two disparate tasks. |
| 地址 |
Redmond WA US |
