-
公开(公告)号:US20210224659A1
公开(公告)日:2021-07-22
申请号:US17227010
申请日:2021-04-09
Applicant: Google LLC
Inventor: Geoffrey E. Hinton , Alexander Krizhevsky , Ilya Sutskever , Nitish Srivastava
Abstract: A system for training a neural network. A switch is linked to feature detectors in at least some of the layers of the neural network. For each training case, the switch randomly selectively disables each of the feature detectors in accordance with a preconfigured probability. The weights from each training case are then normalized for applying the neural network to test data.
-
公开(公告)号:US11829882B2
公开(公告)日:2023-11-28
申请号:US17227010
申请日:2021-04-09
Applicant: Google LLC
Inventor: Geoffrey E. Hinton , Alexander Krizhevsky , Ilya Sutskever , Nitish Srivastava
Abstract: A system for training a neural network. A switch is linked to feature detectors in at least some of the layers of the neural network. For each training case, the switch randomly selectively disables each of the feature detectors in accordance with a preconfigured probability. The weights from each training case are then normalized for applying the neural network to test data.
-
公开(公告)号:US10977557B2
公开(公告)日:2021-04-13
申请号:US16523884
申请日:2019-07-26
Applicant: Google LLC
Inventor: Geoffrey E. Hinton , Alexander Krizhevsky , Ilya Sutskever , Nitish Srivastava
Abstract: A system for training a neural network. A switch is linked to feature detectors in at least some of the layers of the neural network. For each training case, the switch randomly selectively disables each of the feature detectors in accordance with a preconfigured probability. The weights from each training case are then normalized for applying the neural network to test data.
-
公开(公告)号:US10366329B2
公开(公告)日:2019-07-30
申请号:US15222870
申请日:2016-07-28
Applicant: Google LLC
Inventor: Geoffrey E. Hinton , Alexander Krizhevsky , Ilya Sutskever , Nitish Srivastava
Abstract: A system for training a neural network. A switch is linked to feature detectors in at least some of the layers of the neural network. For each training case, the switch randomly selectively disables each of the feature detectors in accordance with a preconfigured probability. The weights from each training case are then normalized for applying the neural network to test data.
-
-
-