- 专利标题： Iterative transfer of machine-trained network inputs from validation set to training set
-
申请号： US16453622申请日： 2019-06-26
-
公开(公告)号： US11531879B1公开(公告)日： 2022-12-20
- 发明人: Steven L. Teig , Eric A. Sather
- 申请人： Perceive Corporation
- 申请人地址： US CA San Jose
- 专利权人： Perceive Corporation
- 当前专利权人： Perceive Corporation
- 当前专利权人地址： US CA San Jose
- 代理机构： Adeli LLP
- 主分类号： G06N3/08
- IPC分类号： G06N3/08 ; G06F17/16 ; G06N3/04
摘要：
Some embodiments provide a method for training a machine-trained (MT) network. The method uses a first set of training inputs to train parameters of the MT network. The method uses a set of validation inputs to measure error for the MT network as trained by the first set of training inputs. The method adds at least a subset of the validation inputs to the first set of training inputs to create a second set of training inputs. The method uses the second set of training inputs to train the parameters of the MT network. The error measurement is used to modify the training with the second set of training inputs.
信息查询
