利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

113 条记录 (耗时 0.033 秒)

    Learning system for a data processing apparatus
    1.
    发明授权
    Learning system for a data processing apparatus 失效
    一种数据处理设备的学习系统

    公开(公告)号：US5297237A

    公开(公告)日：1994-03-22

    申请号：US913749

    申请日：1992-07-17

    申请人： Ryusuke Masuoka ,  Nobuo Watanabe ,  Takashi Kimoto ,  Akira Kawamura ,  Kazuo Asakawa ,  Jun'ichi Tanahashi

    发明人： Ryusuke Masuoka ,  Nobuo Watanabe ,  Takashi Kimoto ,  Akira Kawamura ,  Kazuo Asakawa ,  Jun'ichi Tanahashi

    IPC分类号： G06N3/08 ,  G06F15/18

    CPC分类号： G06N3/08

    摘要： A learning system is used in a data processing apparatus for learning an input pattern by obtaining an internal-state value necessary for realizing a desired data conversion by performing a pattern conversion defined by the internal-state value and calculating an output pattern corresponding to the input pattern. The learning system comprises a pattern presenting unit for presenting an input pattern group of the subject to be learned for pattern conversion, dividing the input pattern group of the subject to be learned into at least two sets, selecting one of the divided sets, presenting the input pattern group of the selected set to a pattern conversion unit and presenting an input pattern group belonging to all the sets presented up to the current point when the internal-state value to be converged is obtained in accordance with the presentation of the selected set, and an error value calculating unit for calculating an error value representing a magnitude of a non-consistency between an output pattern group outputted in accordance with the presentation and a teacher pattern group representing a pattern to be obtained by the output pattern group.

    摘要翻译： 在用于学习输入模式的数据处理装置中使用学习系统，通过执行由内部状态值定义的模式转换来获得实现所需数据转换所需的内部状态值，并计算与输入对应的输出模式 模式。 该学习系统包括：图案呈现单元，用于呈现要被学习的图案转换的对象的输入图案组，将要学习的被摄体的输入图案组划分为至少两组;选择一个分割组， 根据所选择的集合的呈现，获得所选集合的输入模式组到模式转换单元，并且呈现属于当前点所呈现的所有集合的输入模式组，当满足内部状态值时， 以及误差值计算单元，用于计算表示根据呈现输出的输出图案组与表示由输出图案组获得的图案的教师图案组之间的不一致性的大小的误差值。

    Learning system for a data processing apparatus
    2.
    发明授权
    Learning system for a data processing apparatus 失效
    一种数据处理设备的学习系统

    公开(公告)号：US6023693A

    公开(公告)日：2000-02-08

    申请号：US540030

    申请日：1995-10-06

    申请人： Ryusuke Masuoka ,  Nobuo Watanabe ,  Takashi Kimoto ,  Akira Kawamura ,  Kazuo Asakawa ,  Jun'ichi Tanahashi

    发明人： Ryusuke Masuoka ,  Nobuo Watanabe ,  Takashi Kimoto ,  Akira Kawamura ,  Kazuo Asakawa ,  Jun'ichi Tanahashi

    IPC分类号： G06N3/08 ,  G06F15/18

    CPC分类号： G06N3/08

    摘要： A learning system is used in a data processing apparatus for learning an input pattern by obtaining an internal-state value necessary for realizing a desired data conversion by performing a pattern conversion defined by the internal-state value and calculating an output pattern corresponding to the input pattern. The learning system comprises a pattern presenting unit for presenting an input pattern group of the subject to be learned for pattern conversion, dividing the input pattern group of the subject to be learned into at least two sets, selecting one of the divided sets, presenting the input pattern group of the selected set to a pattern conversion unit and presenting an input pattern group belonging to all the sets presented up to the current point when the internal-state value to be converged is obtained in accordance with the presentation of the selected set, and an error value calculating unit for calculating an error value representing a magnitude of a non-consistency between an output pattern group outputted in accordance with the presentation and a teacher pattern group representing a pattern to be obtained by the output pattern group.

    摘要翻译： 在用于学习输入模式的数据处理装置中使用学习系统，通过执行由内部状态值定义的模式转换来获得实现所需数据转换所需的内部状态值，并计算与输入对应的输出模式 模式。 该学习系统包括：图案呈现单元，用于呈现要被学习的图案转换的对象的输入图案组，将要学习的被摄体的输入图案组划分为至少两组;选择一个分割组， 根据所选择的集合的呈现，获得所选集合的输入模式组到模式转换单元，并且呈现属于当前点所呈现的所有集合的输入模式组，当满足内部状态值时， 以及误差值计算单元，用于计算表示根据呈现输出的输出图案组与表示由输出图案组获得的图案的教师图案组之间的不一致性的大小的误差值。

    Learning system for a data processing apparatus
    3.
    发明授权
    Learning system for a data processing apparatus 失效
    一种数据处理设备的学习系统

    公开(公告)号：US5410636A

    公开(公告)日：1995-04-25

    申请号：US112377

    申请日：1993-08-27

    申请人： Ryusuke Masuoka ,  Nobuo Watanabe ,  Takashi Kimoto ,  Akira Kawamura ,  Kazuo Asakawa ,  Jun'ichi Tanahashi

    发明人： Ryusuke Masuoka ,  Nobuo Watanabe ,  Takashi Kimoto ,  Akira Kawamura ,  Kazuo Asakawa ,  Jun'ichi Tanahashi

    IPC分类号： G06N3/08 ,  G06F15/18

    CPC分类号： G06N3/08

    摘要： A learning system is used in a data processing apparatus for learning an input pattern by obtaining an internal-state value necessary for realizing a desired data conversion by performing a pattern conversion defined by the internal-state value and calculating an output pattern corresponding to the input pattern. The learning system comprises a pattern presenting unit for presenting an input pattern group of the subject to be learned for pattern conversion, dividing the input pattern group of the subject to be learned into at least two sets, selecting one of the divided sets, presenting the input pattern group of the selected set to a pattern conversion unit and presenting an input pattern group belonging to all the sets presented up to the current point when the internal-state value to be converged is obtained in accordance with the presentation of the selected set, and an error value calculating unit for calculating an error value representing a magnitude of a non-consistency between an output pattern group outputted in accordance with the presentation and a teacher pattern group representing a pattern to be obtained by the said output pattern group.

    摘要翻译： 在用于学习输入模式的数据处理装置中使用学习系统，通过执行由内部状态值定义的模式转换来获得实现所需数据转换所需的内部状态值，并计算与输入对应的输出模式 模式。 该学习系统包括：图案呈现单元，用于呈现要被学习的图案转换的对象的输入图案组，将要学习的被摄体的输入图案组划分为至少两组;选择一个分割组， 根据所选择的集合的呈现，获得所选集合的输入模式组到模式转换单元，并且呈现属于当前点所呈现的所有集合的输入模式组，当满足内部状态值时， 以及误差值计算单元，用于计算表示根据呈现输出的输出图案组与表示由所述输出图案组获得的图案的教师图案组之间的不一致性的大小的误差值。

    Learning process system for use with a neural network structure data processing apparatus
    4.
    发明授权
    Learning process system for use with a neural network structure data processing apparatus 失效
    用于神经网络结构数据处理装置的学习过程系统

    公开(公告)号：US5333239A

    公开(公告)日：1994-07-26

    申请号：US3856

    申请日：1993-01-11

    申请人： Nobuo Watanabe ,  Takashi Kimoto ,  Akira Kawamura ,  Ryusuke Masuoka ,  Kazuo Asakawa

    发明人： Nobuo Watanabe ,  Takashi Kimoto ,  Akira Kawamura ,  Ryusuke Masuoka ,  Kazuo Asakawa

    IPC分类号： G06N3/04 ,  G06N3/08 ,  G06F15/18 ,  G06G7/60

    CPC分类号： G06N3/084 ,  G06N3/04

    摘要： A learning process system is provided for a neural network. The neural network is a layered network comprising an input layer, an intermediate layer and an output layer formed of basic units. In the basic units, a plurality of inputs is multiplied by a weight signal and the products are accumulated, thereby supplying the sum of products. An output signal is obtained using a threshold value function in response to the sum of products. An error signal is generated by an error circuit in response to a difference between the output signal obtained from the output layer and a teacher signal. A weight updating signal is determined in a weight learning circuit by obtaining a weight value in which the sum of the error values falls within an allowable range. Thus, the learning is performed in the layered neural network through use of a back propagation method. Through such learning in the layered neural network, an updating quantity to be obtained in the present weight updating cycle is determined in response to a once delayed weight updating quantity signal in a previous weight updating cycle and a twice delayed weight updating quantity obtained at a twice-previous weight updating cycle prior to the previous weight updating cycle.

    摘要翻译： 为神经网络提供学习过程系统。 神经网络是包括由基本单元形成的输入层，中间层和输出层的分层网络。 在基本单位中，将多个输入乘以权重信号，并积累乘积，从而提供乘积之和。 使用响应于乘积之和的阈值函数获得输出信号。 响应于从输出层获得的输出信号和教师信号之间的差异，误差电路产生误差信号。 在权重学习电路中通过获得误差值之和落在容许范围内的权重值来确定权重更新信号。 因此，通过使用反向传播方法在分层神经网络中进行学习。 通过在分层神经网络中的这种学习，响应于先前权重更新周期中的一次延迟加权更新量信号和在两次延迟加权更新量中获得的当前权重更新周期中将获得的更新量 在先前权重更新周期之前的前一权重更新周期。

    Neuro-fuzzy-integrated data processing system
    5.
    发明授权
    Neuro-fuzzy-integrated data processing system 失效
    神经模糊综合数据处理系统

    公开(公告)号：US5875284A

    公开(公告)日：1999-02-23

    申请号：US773576

    申请日：1992-06-09

    申请人： Nobuo Watanabe ,  Akira Kawamura ,  Ryushuke Masuoka ,  Yuri Owada ,  Kazuo Asakawa ,  Shigenori Matsuoka ,  Hiroyuki Okada

    发明人： Nobuo Watanabe ,  Akira Kawamura ,  Ryushuke Masuoka ,  Yuri Owada ,  Kazuo Asakawa ,  Shigenori Matsuoka ,  Hiroyuki Okada

    IPC分类号： G06N3/04 ,  G06N7/04 ,  G06F15/18

    CPC分类号： G06N3/0436 ,  G06N7/046

    摘要： The present invention relates to a data processing system in a hierarchical network configuration for executing applicable data processes in a comprehensible and executable form. The present invention allows data processing capabilities to be established with high precision in a short time based on a fuzzy-neuro-integrated concept. A fuzzy model is generated by a data processing system in the form of membership functions and fuzzy rules as technical information relating to a control target. According to this fuzzy model, a weight value of the connection between neurons is set and a pre-wired neural network is established. Then, the data of the control target are learned by the neural network. The connection state and a weight value of the neural network after the learning enable tuning of the fuzzy model.

    摘要翻译： PCT No.PCT / JP91 / 00334 Sec。 371日期：1992年6月9日 102（e）日期1992年6月9日PCT 1991年3月12日PCT公布。 出版物WO91 / 14226 日期1991年9月19日本发明涉及分层网络配置中的数据处理系统，用于以可理解和可执行的形式执行适用的数据处理。 本发明允许基于模糊神经综合概念在短时间内以高精度建立数据处理能力。 以隶属函数和模糊规则的形式由数据处理系统生成模糊模型作为与控制目标相关的技术信息。 根据该模糊模型，设置神经元之间的连接的权重值，建立预接线神经网络。 然后，通过神经网络学习控制目标的数据。 连接状态和神经网络的权重值在学习后能够调整模糊模型。

    STORE SYSTEM AND SALES REGISTRATION METHOD
    7.
    发明申请
    STORE SYSTEM AND SALES REGISTRATION METHOD 有权
    存储系统和销售注册方法

    公开(公告)号：US20120047039A1

    公开(公告)日：2012-02-23

    申请号：US13214395

    申请日：2011-08-22

    申请人： Masahito Sano ,  Hiroyuki Ueda ,  Nobuo Watanabe ,  Hiroyuki Koyama

    发明人： Masahito Sano ,  Hiroyuki Ueda ,  Nobuo Watanabe ,  Hiroyuki Koyama

    IPC分类号： G06Q20/00

    CPC分类号： G07G3/003 ,  G06Q20/20 ,  G06Q20/208 ,  G07G1/0063 ,  G07G1/01

    摘要： According to one embodiment, a store system includes: an image output section configured to output an image picked up by an image pickup section; an object recognizing section configured to recognize a specific object by reading a feature value of the output image; a check-image display section configured to display, on a display section, at least an image concerning the recognized object; and a problem solving section configured to receive, when there is a problem in the recognition of the object, an instruction indicating the problem and solve the problem according to content of the received instruction.

    摘要翻译： 根据一个实施例，存储系统包括：图像输出部分，被配置为输出由图像拾取部拾取的图像; 对象识别部，被配置为通过读取输出图像的特征值来识别特定对象; 检查图像显示部，被配置为在显示部上至少显示与识别对象有关的图像; 以及问题解决部，被配置为当在所述对象的识别中存在问题时接收指示所述问题的指令，并且根据所接收的指令的内容来解决所述问题。

    STORE SYSTEM AND SALES REGISTRATION METHOD
    8.
    发明申请
    STORE SYSTEM AND SALES REGISTRATION METHOD 有权
    存储系统和销售注册方法

    公开(公告)号：US20120047037A1

    公开(公告)日：2012-02-23

    申请号：US13214368

    申请日：2011-08-22

    申请人： Hiroyuki Ueda ,  Masahito Sano ,  Nobuo Watanabe ,  Hiroyuki Koyama

    发明人： Hiroyuki Ueda ,  Masahito Sano ,  Nobuo Watanabe ,  Hiroyuki Koyama

    IPC分类号： G06Q20/00

    CPC分类号： G07G1/0054 ,  G06K9/00 ,  G06K2209/17 ,  G06Q20/208 ,  G06Q30/06 ,  G06T1/20 ,  G06T7/001 ,  G06T2207/10024 ,  G06T2207/30128

    摘要： According to one embodiment, a store system includes: an image output section configured to output an image picked up by an image pickup section; an object recognizing section configured to recognize a specific object by reading a feature value of the output image; a similarity determining section configured to calculate similarity indicating to which degree the recognized object is similar to a reference image of the object determined in advance and determine whether the calculated similarity exceeds a threshold set in advance; and a defective informing section configured to inform, if the similarity determining section determines that the calculated similarity does not exceed the threshold set in advance, that the object is not recognized as a regular commodity.

    摘要翻译： 根据一个实施例，存储系统包括：图像输出部分，被配置为输出由图像拾取部拾取的图像; 对象识别部，被配置为通过读取输出图像的特征值来识别特定对象; 相似度确定部分，被配置为计算相似度，该相似度指示所识别的对象的程度与预先确定的对象的参考图像相似，并且确定所计算的相似度是否超过预先设定的阈值; 以及缺陷通知部，被配置为通知相似度确定部，如果所计算的相似度不超过预先设定的阈值，则该对象不被识别为常规商品。