利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

15 条记录 (耗时 0.015 秒)

    Neuronal data processing system and adaptation method therefor
    2.
    发明公开
    Neuronal data processing system and adaptation method therefor 失效
    神经元Datenverarbeitungssystem和Anpassungsverfahren。

    公开(公告)号：EP0405174A2

    公开(公告)日：1991-01-02

    申请号：EP90110384.6

    申请日：1990-05-31

    申请人： YOZAN INC. ,  SHARP KABUSHIKI KAISHA

    发明人： Takatori, Sunao ,  Kumagai, Ryohei ,  Yamamoto, Makoto ,  Matsumoto, Koji

    IPC分类号： G06F15/80

    CPC分类号： G06N3/08

    摘要： An adaptation method for a data processing system comprising a plurality of neurons each of which outputs an output according to a comparison between a sum of multiplied inputs by weights and a threshold, characterized in the following steps:
    The threshold of the neuron which has generated significant output at certain point of time is compulsorily increased to a maximal value;
    The weight of the neuron is adapted for a constant value of the inputs; and the threshold is decreased to a value at the point.

    摘要翻译： 一种用于数据处理系统的适应方法，包括多个神经元，每个神经元根据权重和相乘输入之和之间的比较来输出输出，其特征在于以下步骤：产生显着的神经元的阈值 在某个时间点的输出强制增加到最大值; 神经元的权重适用于输入的恒定值; 并且阈值减小到该点处的值。

    Neural network
    3.
    发明公开
    Neural network 失效
    数据处理系统

    公开(公告)号：EP0422659A3

    公开(公告)日：1991-07-03

    申请号：EP90119532.1

    申请日：1990-10-11

    申请人： YOZAN INC. ,  SHARP KABUSHIKI KAISHA

    发明人： Takatori, Sunao ,  Kumagai, Ryohei ,  Matsumoto, Koji ,  Yamamoto, Makoto

    IPC分类号： G06F15/80

    CPC分类号： G06N3/063

    摘要： (1) A data processing system comprising:
    a plurality of operational amplifiers;
    a plurality of input leading wires supplying input signals to each operational amplifier, respectively;
    a plurality of switching circuits connected with each output of the operational amplifier, respectively, when value of output signals for each operational amplifier exceeds the predetermined value;
    an output leading wire connected with the switching circuits for supplying output signals of each the switching circuit to input side of the operational amplifiers though variable resistance as well as outputting them to the out­side.

    Neural network
    4.
    发明公开
    Neural network 失效
    神经网络

    公开(公告)号：EP0422659A2

    公开(公告)日：1991-04-17

    申请号：EP90119532.1

    申请日：1990-10-11

    申请人： YOZAN INC. ,  SHARP KABUSHIKI KAISHA

    发明人： Takatori, Sunao ,  Kumagai, Ryohei ,  Matsumoto, Koji ,  Yamamoto, Makoto

    IPC分类号： G06F15/80

    CPC分类号： G06N3/063

    摘要： (1) A data processing system comprising:
    a plurality of operational amplifiers;
    a plurality of input leading wires supplying input signals to each operational amplifier, respectively;
    a plurality of switching circuits connected with each output of the operational amplifier, respectively, when value of output signals for each operational amplifier exceeds the predetermined value;
    an output leading wire connected with the switching circuits for supplying output signals of each the switching circuit to input side of the operational amplifiers though variable resistance as well as outputting them to the out­side.

    摘要翻译： （1）一种数据处理系统，包括：多个运算放大器; 多个输入引线，分别向每个运算放大器提供输入信号; 当每个运算放大器的输出信号的值超过预定值时，分别与运算放大器的每个输出端连接的多个开关电路; 与开关电路连接的输出引线，用于通过可变电阻将每个开关电路的输出信号提供给运算放大器的输入侧，并且将它们输出到外部。

    A method of selecting characteristics data for a data processing system
    9.
    发明公开
    A method of selecting characteristics data for a data processing system 失效
    选择数据处理系统的特征数据的方法

    公开(公告)号：EP0435099A3

    公开(公告)日：1993-02-24

    申请号：EP90124142.2

    申请日：1990-12-13

    申请人： YOZAN INC. ,  SHARP KABUSHIKI KAISHA

    发明人： Takatori, Sunao ,  Kumagai, Ryohei ,  Matsumoto, Koji ,  Yamamoto, Makoto

    IPC分类号： G06F15/80

    CPC分类号： G06K9/6228 ,  G06N3/02

    摘要： A method of selecting characteristics data for a data processing system from a group of input data for reducing data volume of each input data by said data processing system having structure of a neural network or the structure equivalent thereto, where an input data consists of a plurality of said characteristics data, comprising steps of; storing outputs of said input data; selecting a specific characteristics data of a pair of different input data; exchanging said characteristics data of said input data pair with each other; comparing outputs from said data processing system in response to said input data before and after the exchange of said characteristics data; and removing said characteristics data from said input data in said group, when a difference between said outputs before and after is comparatively small.

    A method of selecting characteristics data for a data processing system
    10.
    发明公开
    A method of selecting characteristics data for a data processing system 失效
    KenndatenauswahlverfahrenfürDatenverarbeitungssystem。

    公开(公告)号：EP0435099A2

    公开(公告)日：1991-07-03

    申请号：EP90124142.2

    申请日：1990-12-13

    申请人： YOZAN INC. ,  SHARP KABUSHIKI KAISHA

    发明人： Takatori, Sunao ,  Kumagai, Ryohei ,  Matsumoto, Koji ,  Yamamoto, Makoto

    IPC分类号： G06F15/80

    CPC分类号： G06K9/6228 ,  G06N3/02

    摘要： A method of selecting characteristics data for a data processing system from a group of input data for reducing data volume of each input data by said data processing system having structure of a neural network or the structure equivalent thereto, where an input data consists of a plurality of said characteristics data, comprising steps of; storing outputs of said input data; selecting a specific characteristics data of a pair of different input data; exchanging said characteristics data of said input data pair with each other; comparing outputs from said data processing system in response to said input data before and after the exchange of said characteristics data; and removing said characteristics data from said input data in said group, when a difference between said outputs before and after is comparatively small.

    摘要翻译： 一种从一组输入数据中选择特征数据的方法，用于通过具有神经网络结构或等同于其的结构的所述数据处理系统减少每个输入数据的数据量，其中输入数据由多个 的所述特征数据，包括以下步骤： 存储所述输入数据的输出; 选择一对不同输入数据的特定特征数据; 将所述输入数据对的所述特征数据彼此交换; 比较来自所述数据处理系统的输出响应于在所述特征数据的交换之前和之后的所述输入数据; 并且当所述输出之前和之后的差相对较小时，从所述组中的所述输入数据中去除所述特性数据。