- 专利标题： Pruning redundant neurons and kernels of deep convolutional neural networks
-
申请号： US15788523申请日： 2017-10-19
-
公开(公告)号： US11093832B2公开(公告)日： 2021-08-17
- 发明人: Chun-Fu Chen , Jui-Hsin Lai , Ching-Yung Lin , Guangnan Ye , Ruichi Yu
- 申请人： International Business Machines Corporation
- 申请人地址： US NY Armonk
- 专利权人： International Business Machines Corporation
- 当前专利权人： International Business Machines Corporation
- 当前专利权人地址： US NY Armonk
- 代理机构： Patterson + Sheridan, LLP
- 主分类号： G06N3/08
- IPC分类号： G06N3/08 ; G06N3/04
摘要：
Method and apparatus for optimizing a convolutional neural network (CNN). A respective measure of importance is calculated for each of a plurality of elements within a CNN. A first one of the measures of importance is calculated by back propagating a second one of the measures of importance through the CNN. One or more of the plurality of elements is pruned from the CNN, based on the calculated measures of importance.
公开/授权文献
信息查询
