发明授权
- 专利标题: Optimizing execution of a neural network based on operational performance parameters
-
申请号: US17016908申请日: 2020-09-10
-
公开(公告)号: US11816568B2公开(公告)日: 2023-11-14
- 发明人: Sek Meng Chai , Jagadeesh Kandasamy
- 申请人: Latent AI, Inc.
- 申请人地址: US CA Menlo Park
- 专利权人: Latent AI, Inc.
- 当前专利权人: Latent AI, Inc.
- 当前专利权人地址: US CA Menlo Park
- 代理机构: Park, Vaughan, Fleming & Dowler LLP
- 主分类号: G06N3/08
- IPC分类号: G06N3/08 ; H04L41/16 ; G06N5/04 ; G06N3/04 ; G06F16/901 ; G06F17/18 ; G06N3/10
摘要:
The disclosed embodiments relate to a system that optimizes execution of a DNN based on operational performance parameters. During operation, the system collects the operational performance parameters from the DNN during operation of the DNN, wherein the operational performance parameters include parameters associated with operating conditions for the DNN, parameters associated with resource utilization during operation of the DNN, and parameters associated with accuracy of results produced by the DNN. Next, the system uses the operational performance parameters to update the DNN model to improve performance and efficiency during execution of the DNN.
公开/授权文献
信息查询