- 专利标题: Method for synthesizing a neural network
-
申请号: US15413283申请日: 2017-01-23
-
公开(公告)号: US10546231B2公开(公告)日: 2020-01-28
- 发明人: Shabab Bazrafkan , Joe Lemley
- 申请人: FotoNation Limited
- 申请人地址: IE Galway
- 专利权人: FotoNation Limited
- 当前专利权人: FotoNation Limited
- 当前专利权人地址: IE Galway
- 主分类号: G06N3/04
- IPC分类号: G06N3/04
摘要:
Synthesizing a neural network from a plurality of component neural networks is disclosed. The method comprises mapping each component network to a respective graph node where each node is first labelled in accordance with the structure of a corresponding layer of the component network and a distance of the node from one of a given input or output. The graphs for each component network are merged into a single merged graph by merging nodes from component network graphs having the same first structural label. Each node of the merged graph is second labelled in accordance with the structure of the corresponding layer of the component network and a distance of the node from the other of a given input or output. The merged graph is contracted by merging nodes of the merged graph having the same second structural label. The contracted-merged graph is mapped to a synthesized neural network.
公开/授权文献
- US20180211155A1 Method for synthesizing a neural network 公开/授权日:2018-07-26
信息查询