利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

4 条记录 (耗时 0.019 秒)

    Method and apparatus for checking input-output characteristic of neural network
    1.
    发明授权
    Method and apparatus for checking input-output characteristic of neural network 失效
    用于检查神经网络输入输出特性的方法和装置

    公开(公告)号：US5333238A

    公开(公告)日：1994-07-26

    申请号：US936635

    申请日：1992-08-28

    申请人： Yukinori Kakazu ,  Takao Yoneda ,  Tomonari Kato ,  Kazuya Hattori

    发明人： Yukinori Kakazu ,  Takao Yoneda ,  Tomonari Kato ,  Kazuya Hattori

    IPC分类号： G06F15/18 ,  G06G7/60 ,  G06N3/04 ,  G06N3/10 ,  G06N99/00

    CPC分类号： G06N3/10 ,  G06N3/04

    摘要： An apparatus for checking the input-output characteristic of a neural network which has an input layer, an intermediate layer and an output layer. Plural nodes of the input layer are related to plural nodes of the intermediate layer with plural connection weights while the plural nodes of the intermediate layer are also related to plural nodes of the output layer with plural connection weights. One of the nodes of the input layer is selected as a variable input element while the rest of the nodes are regarded as fixed input elements. A variable data input to the variable input element is varied within a predetermined variation range, while data input to the fixed input elements are fixed, so as to detect how the components of output data from the output layer change. The detected changes of the components of the output data are displayed as the input-output characteristic of the neural network.

    摘要翻译： 一种用于检查具有输入层，中间层和输出层的神经网络的输入 - 输出特性的装置。 输入层的多个节点与具有多个连接权重的中间层的多个节点相关，而中间层的多个节点也与具有多个连接权重的输出层的多个节点相关。 选择输入层的一个节点作为可变输入元素，而将其余节点视为固定输入元素。 输入到可变输入元件的可变数据在预定变化范围内变化，而输入到固定输入元件的数据是固定的，以便检测来自输出层的输出数据的分量如何变化。 检测到的输出数据的分量的变化被显示为神经网络的输入 - 输出特性。

    Method and apparatus for performing learning in a neural network
    2.
    发明授权
    Method and apparatus for performing learning in a neural network 失效
    用于在神经网络中执行学习的方法和装置

    公开(公告)号：US5355434A

    公开(公告)日：1994-10-11

    申请号：US931324

    申请日：1992-08-18

    申请人： Takao Yoneda ,  Tomonari Kato ,  Kazuya Hattori ,  Masashi Yamanaka ,  Shiho Hattori

    发明人： Takao Yoneda ,  Tomonari Kato ,  Kazuya Hattori ,  Masashi Yamanaka ,  Shiho Hattori

    IPC分类号： G06N3/08 ,  G06N3/10 ,  G06F15/18

    CPC分类号： G06N3/10 ,  G06N3/08

    摘要： An apparatus for carrying out learning operation of a neural network which has an input layer, an intermediate layer and an output layer. Plural nodes of the input layer are related to plural nodes of the intermediate layer with plural connection weights, while the plural nodes of the intermediate layer are also related to plural nodes of the output layer with plural connection weights. Although input data composed of plural components and teaching data composed of plural components are used in learning operation, some of the components are ineffective for the purpose of learning operation. During error calculation between output data from the neural network and the teaching data, the apparatus judges whether each of the components of the teaching data is effective or ineffective, and output errors corresponding to the ineffective components are regarded as zero. The connection weights are thereafter corrected based upon the calculated errors. The apparatus further comprises means for adding new input data and teaching data into a data base, and means for calculating a degree of heterogeneousness of the new teaching data. The new input data and teaching data are added to the data base only when the degree of heterogeneousness is smaller than a predetermined value.

    摘要翻译： 一种用于执行具有输入层，中间层和输出层的神经网络的学习操作的装置。 输入层的多个节点与具有多个连接权重的中间层的多个节点相关，而中间层的多个节点也与具有多个连接权重的输出层的多个节点相关。 虽然在学习操作中使用由多个分量组成的输入数据和由多个分量组成的教学数据，但是为了学习操作的目的，一些组件是无效的。 在神经网络的输出数据与教学数据的误差计算期间，设备判断教学数据的各个成分是否有效或无效，与无效分量相对应的输出误差为零。 然后根据计算的误差校正连接权重。 该装置还包括用于将新的输入数据和教学数据添加到数据库中的装置，以及用于计算新教学数据的异质程度的装置。 仅当异质度小于预定值时，才将新的输入数据和教学数据添加到数据库。