发明申请
US20080301075A1 METHOD OF TRAINING A NEURAL NETWORK AND A NEURAL NETWORK TRAINED ACCORDING TO THE METHOD
审中-公开
训练神经网络的方法和根据该方法训练的神经网络
- 专利标题: METHOD OF TRAINING A NEURAL NETWORK AND A NEURAL NETWORK TRAINED ACCORDING TO THE METHOD
- 专利标题(中): 训练神经网络的方法和根据该方法训练的神经网络
-
申请号: US11936756申请日: 2007-11-07
-
公开(公告)号: US20080301075A1公开(公告)日: 2008-12-04
- 发明人: George Bolt , John Manslow , Alan McLachlan
- 申请人: George Bolt , John Manslow , Alan McLachlan
- 申请人地址: GB Hampshire
- 专利权人: Neural Technologies, Ltd.
- 当前专利权人: Neural Technologies, Ltd.
- 当前专利权人地址: GB Hampshire
- 优先权: GB0209780.6 20020429
- 主分类号: G06N3/08
- IPC分类号: G06N3/08
摘要:
A neural network comprises trained interconnected neurons. The neural network is configured to constrain the relationship between one or more inputs and one or more outputs of the neural network so the relationships between them are consistent with expectations of the relationships; and/or the neural network is trained by creating a set of data comprising input data and associated outputs that represent archetypal results and providing real exemplary input data and associated output data and the created data to neural network. The real exemplary output data and the created associated output data is compared to the actual output of the neural network, which is adjusted to create a best fit to the real exemplary data and the created data.
信息查询