-
公开(公告)号：US4908864A
公开(公告)日：1990-03-13
申请号：US034060
申请日：1987-04-02
IPC分类号： G10L15/06
CPC分类号： G10L15/063
摘要： Inputted voice signals are analyzed in units of syllables. Each syllable is compared with standard syllables preregistered in a memory and thereby recognized but corrections may be made on erroneous recognitions by referencing a dictionary or entering a command. Each standard pattern is associated with phonological information on the neighborhood in a voice signal from where it was extracted and may be updated by another pattern having the same phonological information. Temporal sequences of correct and erroneous recognitions of individual syllables as well as whole syllables are stored and referenced in determining whether a standard pattern should be updated. A maximum pattern number may be set for each syllable.
摘要翻译： 输入的语音信号以音节为单位进行分析。 将每个音节与预先登记在存储器中的标准音节进行比较，从而识别，但可以通过引用字典或输入命令来对错误的识别进行修正。 每个标准模式与来自其提取的语音信号中的邻域的语音信息相关联，并且可以由具有相同语音信息的另一模式更新。 在确定是否应更新标准模式时，存储和引用单个音节以及整个音节的正确和错误识别的时间序列。 可以为每个音节设置最大花样编号。
-
2.发明授权Column dot formation in an ink jet system printer of the charge amplitude controlling type 失效在电荷幅度控制型喷墨系统打印机中形成柱点
公开(公告)号：US4424518A
公开(公告)日：1984-01-03
申请号：US256917
申请日：1981-04-23
摘要： An ink jet system printer of the charge amplitude controlling type prints a desired symbol in a dot matrix fashion on a recording paper. Dots for forming a column of the dot matrix are formed in an up and down manner in order to increase the distance provided between two adjacent travelling ink droplets. When a first ink droplet is directed to a dot position higher than a dot position to which a following ink droplet is directed, the positions must be separated on the recording paper by at least a first deadzone of a first dimension. When a first ink droplet is directed to a dot position lower than a dot position to which a following ink droplet is directed, the positions must be separated on the recording paper by at least a second deadzone. The second deadzone is shorter than the first deadzone.
摘要翻译： 电荷幅度控制型的喷墨系统打印机以点阵方式在记录纸上打印期望的符号。 用于形成点阵列的点以上下方式形成，以便增加两个相邻行进墨滴之间的距离。 当第一墨滴被引导到高于后续墨滴指向的点位置的点位置时，位置必须在记录纸上被至少第一维度的第一死区分开。 当第一墨滴指向低于后续墨滴指向的点位置的点位置时，位置必须在记录纸上至少分开第二死区。 第二个死区比第一个死区短。
-
公开(公告)号：US5283838A
公开(公告)日：1994-02-01
申请号：US685596
申请日：1991-04-15
申请人： Fumio Togawa , Toru Ueda , Takashi Aramaki , Yasushi Ishizuka
发明人： Fumio Togawa , Toru Ueda , Takashi Aramaki , Yasushi Ishizuka
CPC分类号： G06K9/6272 , G06N3/10
摘要： When performing learning for a neural network, a plurality of learning vectors which belong to an arbitrary category are used, and self-organization learning in the category is carried out. As a result, the plurality of learning vectors which belong to the category are automatically clustered, and the contents of weight vectors in the neural network are set to representative vectors which exhibit common features of the learning vectors of each cluster. Then, teacher-supervised learning is carried out for the neural network, using the thus set contents of the weight vectors as initial values thereof. In the learning process, an initial value of each weight vector is set to the representative vector of each cluster obtained by clustering. Therefore, the number of calculations required until the teacher-supervised learning is converged is greatly reduced.
摘要翻译： 当对神经网络进行学习时，使用属于任意类别的多个学习向量，并且执行该类别中的自组织学习。 结果，属于该类别的多个学习向量被自动聚类，将神经网络中权重向量的内容设置为表示每个簇的学习向量的共同特征的代表向量。 然后，对神经网络进行教师监督学习，使用这样设定的权重向量的内容作为其初始值。 在学习过程中，将每个权重向量的初始值设置为通过聚类获得的每个簇的代表向量。 因此，在教师监督学习融合之前所需的计算量大大减少。
-
公开(公告)号：US5033006A
公开(公告)日：1991-07-16
申请号：US489508
申请日：1990-03-07
申请人： Yasushi Ishizuka , Fumio Togawa , Toru Ueda
发明人： Yasushi Ishizuka , Fumio Togawa , Toru Ueda
CPC分类号： G06K9/6272 , G06N3/082
摘要： A self-extending shape neural-network is capable of a self-extending operation in accordance with the studying results. The self-extending shape neural-network has initially minimum number of the intermediate layers and the number of the nodes (units) within each layer by the self-extension of the network construction so as to shorten the studying time and the discriminating time. This studying may be effected efficiently by the studying being directed towards the focus when the studying is not focused.
摘要翻译： 自扩展形状神经网络能够根据研究结果进行自我扩展操作。 自扩展形状神经网络通过网络结构的自扩展，开始最小数量的中间层和每层内的节点数（单位数），以缩短学习时间和辨别时间。 在学习不集中的时候，通过学习针对焦点，可以有效地实现这种学习。
-
5.发明授权Character recognition device which divides a single character region into subregions to obtain a character code 失效字符识别装置，其将单个字符区域划分成子区域以获得字符代码
公开(公告)号：US5271068A
公开(公告)日：1993-12-14
申请号：US871075
申请日：1992-04-20
申请人： Toru Ueda , Yasushi Ishizuka , Fumio Togawa
发明人： Toru Ueda , Yasushi Ishizuka , Fumio Togawa
CPC分类号： G06K9/4609 , G06K9/6271 , G06K2209/01
摘要： A character recongintion device has a subdivider, a features calculator and a character code recognition device. Image data for a single character area is extracted from scanned character image data and input to the subdivider. This subdivider divides the image data for the single character area into subregions. The features calculator calculates quantified features in each subregion based on a degree of resemblance between a template and image data in the subregions. When the features of each subregion are calculated for all subregions constituting the single character area, a character code corresponding to the scanned character image data is recognized by the character code recognition device based on the quantified features of each of all subregions.
摘要翻译： 字符识别装置具有分割器，特征计算器和字符代码识别装置。 从扫描的字符图像数据中提取单个字符区域的图像数据并输入到分割器。 该分割器将单个字符区域的图像数据划分为子区域。 特征计算器基于子区域中的模板和图像数据之间的相似程度，计算每个子区域中的量化特征。 当针对构成单个字符区域的所有子区域计算每个子区域的特征时，基于每个子区域的量化特征，由字符代码识别装置识别与扫描的字符图像数据相对应的字符代码。
-
6.发明授权
公开(公告)号：US5263107A
公开(公告)日：1993-11-16
申请号：US647823
申请日：1991-01-31
申请人： Toru Ueda , Fumio Togawa
发明人： Toru Ueda , Fumio Togawa
CPC分类号： G06K9/4628 , G06K9/6272 , G06K2209/01 , G06K2209/011
摘要： A neural network system and method of operating same wherein input data are initialized, then mapped onto a predetermined array for learning or recognition. The mapped information is divided into sub-input data or receptive fields, which are used for comparison of the input information with prelearned information having similar features, thereby allowing for correct classification of the input information. The receptive fields are shifted before the classification process, in order to generate a closest match between features which may be shifted at the time of input, and weights of the input information are updated based upon the closest-matching shifted position of the input information.
摘要翻译： 一种神经网络系统和操作方法，其中输入数据被初始化，然后映射到用于学习或识别的预定阵列上。 映射信息被分为子输入数据或接收字段，用于将输入信息与具有相似特征的预先记录的信息进行比较，从而允许输入信息的正确分类。 接收场在分类处理之前被移位，以便在输入时产生可能被移位的特征之间产生最接近的匹配，并且基于输入信息的最匹配的移位位置来更新输入信息的权重。
-
公开(公告)号：US5119438A
公开(公告)日：1992-06-02
申请号：US491039
申请日：1990-03-09
申请人： Toru Ueda , Yasushi Ishizuka , Fumio Togawa
发明人： Toru Ueda , Yasushi Ishizuka , Fumio Togawa
CPC分类号： G06K9/6857 , G06K9/6227 , G06K9/6807
摘要： A recognizing apparatus is provided for recognizing a class to which an inputted characteristic pattern belongs from among a plurality of classes to be discriminated using a neural network. The classes are classified into a plurality of categories. The apparatus includes a network selecting portion for selecting a category to which the inputted characteristic pattern belongs and for selecting a neural network for use in discriminating the class to which the inputted characteristic pattern belongs in the selected category. The apparatus further includes a network memory portion, a network setting portion and a details discriminating portion. The network memory portion stores structures of a plurality of neural networks which have finished learning for respective categories, weights of the neural networks set by the learning and a plurality of discriminating algorithms to be used when the classes are discriminated by the neural networks. The network setting portion sets the structure and weights of a neural network selected by the network selecting portion and a discriminating alogrithm appropriate to the selected category. The details discriminating portion recognizes the class to which the inputted characteristic pattern belongs by performing the details discriminating operation using the neural network set by the neural network setting portion.
摘要翻译： 提供一种识别装置，用于使用神经网络识别要被区分的多个类别中输入的特征模式所属的类别。 这些课程分为多个类别。 该装置包括网络选择部分，用于选择输入的特征模式所属的类别，并用于选择神经网络以用于区分所选类别中输入的特征模式所属的类别。 该装置还包括网络存储器部分，网络设置部分和细节鉴别部分。 网络存储器部分存储已经完成各种类别的学习的多个神经网络的结构，通过学习设置的神经网络的权重以及当神经网络识别类时要使用的多个鉴别算法。 网络设置部分设置由网络选择部分选择的神经网络的结构和权重以及适合于所选类别的识别算法。 细节识别部分通过使用由神经网络设置部分设置的神经网络执行细节识别操作来识别所输入的特征模式所属的类别。
-
公开(公告)号：US5276769A
公开(公告)日：1994-01-04
申请号：US924585
申请日：1992-08-06
申请人： Toru Ueda , Yasushi Ishizuka , Fumio Togawa
发明人： Toru Ueda , Yasushi Ishizuka , Fumio Togawa
CPC分类号： G06K9/6272 , G06N3/08
摘要： A learning apparatus for use in a neural network system which has a plurality of classes representing different meanings. The learning apparatus is provided for learning a number of different patterns, inputted by input vectors, and classified in different classes. The learning apparatus is constructed by a computer and it includes a section for producing a plurality of output vectors representing different classes in response to an input vector, a section for obtaining a first largest output vector of all the output vectors, a section for obtaining a second largest output vector of all the output vectors, and a section for setting predetermined weights to the first and second largest output vectors, respectively, such that the first largest output vector is made larger, and the second largest output vector is made smaller. Furthermore, a section for determining a ratio of the weighted first and second largest output vectors, respectively, is included. If the determined ratio is smaller than a predetermined value, the weighted first and second largest output vectors are further weighted to be made further larger and smaller, respectively.
摘要翻译： 一种用于神经网络系统的学习装置，其具有表示不同含义的多个类别。 提供学习装置，用于学习由输入向量输入并分类为不同类别的多个不同模式。 学习装置由计算机构成，它包括一个部分，用于响应于输入向量产生表示不同类别的多个输出向量，用于获得所有输出向量的第一最大输出向量的部分， 所有输出向量的第二大输出向量，以及用于分别对第一和第二最大输出向量设置预定权重的部分，使得第一最大输出向量变大，并且使第二大输出向量更小。 此外，包括分别用于确定加权的第一和第二最大输出向量的比率的部分。 如果确定的比率小于预定值，则加权的第一和第二最大输出向量进一步被加权以进一步越来越大。
-
9.发明授权Character recognition device which divides a single character region into subregions to obtain a character code 失效字符识别装置，其将单个字符区域划分成子区域以获得字符代码
公开(公告)号：US5151951A
公开(公告)日：1992-09-29
申请号：US667340
申请日：1991-03-11
申请人： Toru Ueda , Yasushi Ishizuka , Fumio Togawa , Takashi Aramaki
发明人： Toru Ueda , Yasushi Ishizuka , Fumio Togawa , Takashi Aramaki
CPC分类号： G06K9/4642 , G06K2209/01
摘要： A character recognition device has a subdivider, a features calculator and a character code recognition device. Image data for a single character area is extracted from scanned character image data and input to the subdivider. This subdivider divides the image data for the single character area into subregions. The features calculator calculates quantified features in each subregion based on a degree of resemblance between a template and image data in the subregions. When the features of each subregion are calculated for all subregions constituting the single character area, a character code corresponding to the scanned character image data is recognized by the character code recognition device based on the quantified features of each of all subregions.
摘要翻译： 字符识别装置具有分割器，特征计算器和字符代码识别装置。 从扫描的字符图像数据中提取单个字符区域的图像数据并输入到分割器。 该分割器将单个字符区域的图像数据划分为子区域。 特征计算器基于子区域中的模板和图像数据之间的相似程度，计算每个子区域中的量化特征。 当针对构成单个字符区域的所有子区域计算每个子区域的特征时，基于每个子区域的量化特征，由字符代码识别装置识别与扫描的字符图像数据相对应的字符代码。
-
公开(公告)号：US4465735A
公开(公告)日：1984-08-14
申请号：US422464
申请日：1982-09-23
申请人： Fumio Togawa , Shigeo Aoyama
发明人： Fumio Togawa , Shigeo Aoyama
CPC分类号： G11B5/706 , G11B5/70673 , G11B5/70694 , Y10S428/90 , Y10T428/257 , Y10T428/269 , Y10T428/2991 , Y10T428/31678
摘要： An improved magnetic recording medium suitable for high density recording is disclosed, which has a squareness ratio in the vertical direction of 0.6 or more and an orientation ratio (squareness ratio in the vertical direction/squareness ratio in the lengthwise direction) of 0.7 or more, prepared from acicular magnetic iron oxide particles having crystalline magnetic anisotropy and a ratio of Fe.sup.2+ /Fe.sup.3+ of 0.05 or less uniformly cobalt-doped, the particles having preferably a particle size of 0.3.mu. or less and an axial ratio of 6 to 10.
摘要翻译： 公开了一种适用于高密度记录的改进的磁记录介质，其垂直方向的垂直度为0.6或更大，并且取向比（垂直方向上的矩形比/长度方向的矩形比）为0.7以上， 由具有结晶磁各向异性的针状磁性氧化铁颗粒和均匀钴掺杂的Fe 2+ + Fe 3+比为0.05或更低的颗粒制备，颗粒的粒度优选为0.3μm以下，轴比为6〜10。
-
-
-
-
-
-
-
-
-
搜索结果
23 条记录 (耗时 0.02 秒)
