发明名称 SYSTEM AND METHOD FOR ADDRESSING OVERFITTING IN A NEURAL NETWORK
摘要 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.
申请公布号 US2016335540(A1) 申请公布日期 2016.11.17
申请号 US201615222870 申请日期 2016.07.28
申请人 Google Inc. 发明人 Hinton Geoffrey E.;Krizhevsky Alexander;Sutskever Ilya;Srivastva Nitish
分类号 G06N3/08;G06N3/04 主分类号 G06N3/08
代理机构 代理人
主权项 1. (canceled)
地址 Mountain View CA US
您可能感兴趣的专利