| 发明名称 |
TECHNOLOGIES FOR PLATFORM-TARGETED MACHINE LEARNING |
| 摘要 |
Technologies for platform-targeted machine learning include a computing device to generate a machine learning algorithm model indicative of a plurality of classes between which a user input is to be classified and translate the machine learning algorithm model into hardware code for execution on the target platform. The user input is to be classified as being associated with a particular class based on an application of one or more features to the user input, and each of the one or more features has an associated implementation cost indicative of a cost to perform on a target platform on which the corresponding feature is to be applied to the user input. |
| 申请公布号 |
US2017091657(A1) |
申请公布日期 |
2017.03.30 |
| 申请号 |
US201514866895 |
申请日期 |
2015.09.26 |
| 申请人 |
Kida Luis S.;Jain Nilesh K.;Iyer Darshan;Al Safadi Ebrahim |
发明人 |
Kida Luis S.;Jain Nilesh K.;Iyer Darshan;Al Safadi Ebrahim |
| 分类号 |
G06N99/00 |
主分类号 |
G06N99/00 |
| 代理机构 |
|
代理人 |
|
| 主权项 |
1. A computing device for platform-targeted machine learning, the computing device comprising:
a model determination module to generate a machine learning algorithm model indicative of a plurality of classes between which a user input is to be classified, wherein the user input is to be classified as being associated with a particular class based on an application of one or more features to the user input, and wherein each of the one or more features has an associated implementation cost indicative of a cost to perform on a target platform on which the corresponding feature is to be applied to the user input; and a hardware translation module to translate the machine learning algorithm model into hardware code for execution on the target platform. |
| 地址 |
Beaverton OR US |
