- 专利标题: Learning neural network structure
-
申请号: US15813961申请日: 2017-11-15
-
公开(公告)号: US11315019B2公开(公告)日: 2022-04-26
- 发明人: Ofir Nachum , Ariel Gordon , Elad Eban , Bo Chen
- 申请人: Google LLC
- 申请人地址: US CA Mountain View
- 专利权人: Google LLC
- 当前专利权人: Google LLC
- 当前专利权人地址: US CA Mountain View
- 代理机构: Fish & Richardson P.C.
- 主分类号: G06N3/08
- IPC分类号: G06N3/08 ; G06N3/04 ; G06N20/00
摘要:
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training neural networks. In one aspect, a system includes a neural network shrinking engine that is configured to receive a neural network being trained and generate a reduced neural network by a shrinking process. The shrinking process includes training the neural network based on a shrinking engine loss function that includes terms penalizing active neurons of the neural network and removing inactive neurons from the neural network. The system includes a neural network expansion engine that is configured to receive the neural network being trained and generate an expanded neural network by an expansion process including adding new neurons to the neural network and training the neural network based on an expanding engine loss function. The system includes a training subsystem that generates reduced neural networks and expanded neural networks.
公开/授权文献
- US20190147339A1 LEARNING NEURAL NETWORK STRUCTURE 公开/授权日:2019-05-16
信息查询