Invention Grant
- Patent Title: Method for al model transferring with layer and memory randomization
-
Application No.: US16900584Application Date: 2020-06-12
-
Publication No.: US11556859B2Publication Date: 2023-01-17
- Inventor: Yueqiang Cheng , Hefei Zhu
- Applicant: Baidu USA LLC , KUNLUNXIN TECHNOLOGY (BEIJING) COMPANY LIMITED
- Applicant Address: US CA Sunnyvale; CN Beijing
- Assignee: Baidu USA LLC,KUNLUNXIN TECHNOLOGY (BEIJING) COMPANY LIMITED
- Current Assignee: Baidu USA LLC,KUNLUNXIN TECHNOLOGY (BEIJING) COMPANY LIMITED
- Current Assignee Address: US CA Sunnyvale; CN Beijing
- Agency: Womble Bond Dickinson (US) LLP
- Main IPC: G06N20/10
- IPC: G06N20/10 ; G06F9/50 ; G06F12/08

Abstract:
A method to transfer an artificial intelligence (AI) model includes identifying a plurality of layers of the AI model, the plurality of layers organized in a first ordered list. The method further includes randomizing the plurality of layers by reorganizing the first ordered list into a second ordered list, and transferring the plurality of layers of the AI model to a data processing accelerator in an order defined by the second ordered list.
Public/Granted literature
- US20210390463A1 METHOD FOR AI MODEL TRANSFERRING WITH LAYER AND MEMORY RANDOMIZATION Public/Granted day:2021-12-16
Information query