- 专利标题: MODEL-AGNOSTIC INPUT TRANSFORMATION FOR NEURAL NETWORKS
-
申请号: US17566624申请日: 2021-12-30
-
公开(公告)号: US20230214705A1公开(公告)日: 2023-07-06
- 发明人: Pin-Yu Chen , Nandhini Chandramoorthy , Karthik V Swaminathan , Jinjun Xiong , Devansh Paresh Shah , Bo Li
- 申请人: International Business Machines Corporation , The Board of Trustees of the University of Illinois
- 申请人地址: US NY Armonk
- 专利权人: International Business Machines Corporation,The Board of Trustees of the University of Illinois
- 当前专利权人: International Business Machines Corporation,The Board of Trustees of the University of Illinois
- 当前专利权人地址: US NY Armonk
- 主分类号: G06N20/00
- IPC分类号: G06N20/00 ; G06N5/04
摘要:
An input transformation function that transforms input data for a second machine learning system is learned using a first machine learning system, the learning being based on minimizing a summation of a task loss and a post-activation density loss. The input data is transformed using the learned input transformation function to alter the post-activation density to reduce an amount of energy consumed for an inferencing task and the inferencing task is carried out on the transformed input data using the second machine learning system.
信息查询