Invention Grant
- Patent Title: System and method for addressing overfitting in a neural network
- Patent Title (中): 用于解决神经网络过拟合的系统和方法
-
Application No.: US14015768Application Date: 2013-08-30
-
Publication No.: US09406017B2Publication Date: 2016-08-02
- Inventor: Geoffrey E. Hinton , Alexander Krizhevsky , Ilya Sutskever , Nitish Srivastva
- Applicant: Google Inc.
- Applicant Address: US CA Mountain View
- Assignee: Google Inc.
- Current Assignee: Google Inc.
- Current Assignee Address: US CA Mountain View
- Agency: Fish & Richardson P.C.
- Main IPC: G06N3/08
- IPC: G06N3/08 ; G06N3/04
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.
Public/Granted literature
- US20140180986A1 SYSTEM AND METHOD FOR ADDRESSING OVERFITTING IN A NEURAL NETWORK Public/Granted day:2014-06-26
Information query
