Method for training a learning-capable system
    3.
    发明授权
    Method for training a learning-capable system 有权
    培养学习能力的系统的方法

    公开(公告)号:US07801839B2

    公开(公告)日:2010-09-21

    申请号:US10520409

    申请日:2003-07-03

    IPC分类号: G06F15/18

    CPC分类号: G16H50/20 G06F19/00

    摘要: The invention is directed to a method for training at least one learning-capable system comprising the steps of providing a predetermined training data set corresponding to a predetermined number of subjects comprising a predetermined input data set and a predetermined outcome data set, augmenting the input data set and/or the outcome data set, and training each learning-capable system using the augmented input data set and/or the augmented outcome data set.

    摘要翻译: 本发明涉及用于训练至少一个学习能力系统的方法,包括以下步骤:提供对应于预定数量的对象的预定训练数据集,所述预定训练数据集包括预定输入数据集和预定结果数据集,增加输入数据 设置和/或结果数据集,并且使用增强输入数据集和/或增强结果数据集来训练每个具有学习能力的系统。

    Method for training a neural network
    4.
    发明授权
    Method for training a neural network 有权
    训练神经网络的方法

    公开(公告)号:US06968327B1

    公开(公告)日:2005-11-22

    申请号:US10049650

    申请日:2000-08-24

    摘要: A method for training a neural network in order to optimize the structure of the neural network includes identifying and eliminating synapses that have no significant influence on the curve of the risk function. First and second sending neurons are selected that are connected to the same receiving neuron by respective first and second synapses. It is assumed that there is a correlation of response signals from the first and second sending neurons to the same receiving neuron. The first synapse is interrupted and a weight of the second synapse is adapted in its place. The output signals of the changed neural network are compared with the output signals of the unchanged neural network. If the comparison result does not exceed a predetermined level, the first synapse is eliminated, thereby simplifying the structure of the neural network.

    摘要翻译: 用于训练神经网络以优化神经网络的结构的方法包括识别和消除对风险函数的曲线没有显着影响的突触。 选择通过相应的第一和第二突触连接到相同接收神经元的第一和第二发送神经元。 假设存在来自第一和第二发送神经元到相同接收神经元的响应信号的相关性。 第一突触中断,第二突触的重量适应其位置。 将改变的神经网络的输出信号与不变神经网络的输出信号进行比较。 如果比较结果不超过预定水平,则消除第一突触,从而简化了神经网络的结构。

    Method for training a learning-capable system
    8.
    发明申请
    Method for training a learning-capable system 有权
    培养学习能力的系统的方法

    公开(公告)号:US20060248031A1

    公开(公告)日:2006-11-02

    申请号:US10520409

    申请日:2003-07-03

    IPC分类号: G06F15/18 G06N3/02

    CPC分类号: G16H50/20 G06F19/00

    摘要: The invention is directed to a method for training at least one learning-capable system comprising the steps of providing a predetermined training data set corresponding to a predetermined number of subjects comprising a predetermined input data set and a predetermined outcome data set, augmenting the input data set and/or the outcome data set, and training each learning-capable system using the augmented input data set and/or the augmented outcome data set.

    摘要翻译: 本发明涉及用于训练至少一个学习能力系统的方法,包括以下步骤:提供对应于预定数量的对象的预定训练数据集,所述预定训练数据集包括预定输入数据集和预定结果数据集,增加输入数据 设置和/或结果数据集,并且使用增强输入数据集和/或增强结果数据集来训练每个具有学习能力的系统。

    Method for determining competing risks
    10.
    发明授权
    Method for determining competing risks 有权
    确定竞争风险的方法

    公开(公告)号:US07395248B2

    公开(公告)日:2008-07-01

    申请号:US10433740

    申请日:2001-12-07

    IPC分类号: G06F15/18

    CPC分类号: G06N3/02

    摘要: The invention concerns a method for determining competing risks for objects following an initial event based on previously measured or otherwise objectifiable training data patterns, in which several signals obtained from a learning capable system are combined in an objective function in such a way that said learning capable system is rendered capable of detecting or forecasting the underlying probabilities of each of the said competing risks.

    摘要翻译: 本发明涉及一种用于基于先前测量的或其他可客观的训练数据模式来确定初始事件之后的对象的竞争风险的方法,其中从学习能力系统获得的多个信号以目标函数的方式组合,使得所述学习能力 系统能够检测或预测每个所述竞争风险的潜在概率。