- 专利标题： Implementing and Training Computational Efficient Neural Network Architectures Utilizing Layer-Skip Logic
-
申请号： US18598876申请日： 2024-03-07
-
公开(公告)号： US20240303464A1公开(公告)日： 2024-09-12
- 发明人: Nan Du , Tao Wang , Yanqi Zhou , Tao Lei , Yuanzhong Xu , Andrew Mingbo Dai , Zhifeng Chen , Dewen Zeng , Yingwei Cui
- 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
- 主分类号： G06N3/04
- IPC分类号： G06N3/04 ; G06N3/084
摘要：
A method includes providing a first set of data objects to a first skip router of a neural network (NN). The NN includes a first NN layer and a second NN layer. The first set of data objects is subdivided into a first set of skip objects and a first set of non-skip objects based on a first skip logic implemented by the first skip router and a first context of each data object in the first set of data objects. A first set of processed objects is generated based on the first set of non-skip objects and a first layer logic implemented by the first NN layer. Predictions are generated based on a second set of data objects and a second layer logic implemented by the second NN layer. The second set of data objects includes the first set of processed objects and the first set of skip objects.
信息查询
