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

IPC分类号： G06K9/66 ,  G06F15/18 ,  G06K9/62 ,  G06K9/68 ,  G06N3/00 ,  G06N99/00 ,  G06T7/00

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：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

IPC分类号： G06G7/60 ,  G06F15/18 ,  G06K9/66 ,  G06N3/08 ,  G06N3/10 ,  G06N99/00 ,  G11C11/54 ,  G06K9/00

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

IPC分类号： G06F15/18 ,  G06N3/04 ,  G06N3/08 ,  G06N99/00

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。

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

IPC分类号： G06K9/66 ,  G06N3/08 ,  G06F15/18

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。

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

IPC分类号： G06K9/46 ,  G06K9/66

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：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

IPC分类号： G06K9/46 ,  G06K9/66 ,  G06K9/62 ,  G06K9/68

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。

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

IPC分类号： G06F15/18 ,  G06G7/60 ,  G06K9/64 ,  G06K9/66 ,  G06N3/00 ,  G06N99/00 ,  G06K9/62

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：US4908864A

公开(公告)日：1990-03-13

申请号：US034060

申请日：1987-04-02

申请人： Fumio Togawa ,  Mitsuhiro Hakaridani ,  Hiroyuki Iwahashi ,  Toru Ueda

发明人： Fumio Togawa ,  Mitsuhiro Hakaridani ,  Hiroyuki Iwahashi ,  Toru Ueda

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。

公开(公告)号：US20140053213A1

公开(公告)日：2014-02-20

申请号：US14112488

申请日：2012-04-04

申请人： Toru Ueda ,  Keiji Saka ,  Yohichi Eguchi ,  Ryosuke Ohmae ,  Seiji Imanishi ,  Takuya Kinoshita

发明人： Toru Ueda ,  Keiji Saka ,  Yohichi Eguchi ,  Ryosuke Ohmae ,  Seiji Imanishi ,  Takuya Kinoshita

IPC分类号： H04N21/482 ,  H04N21/266

CPC分类号： H04N21/266 ,  H04N21/4122 ,  H04N21/43637 ,  H04N21/4627 ,  H04N21/482

摘要： The monitor (10) of this invention includes: a wireless LAN module (12a); a content selecting section (11b) for selecting one of content sources; a video reception selecting section (11c) for (i) identifying a video transmitting apparatus connected to the selected one of the content sources and (ii) causing the wireless LAN module (12a) to receive a video signal from the identified video transmitting apparatus; and a content switching instructing section (11d) for instructing the identified video transmitting apparatus to transmit a video signal from the selected one of the content sources.

摘要翻译： 本发明的监视器（10）包括：无线LAN模块（12a）; 内容选择部分，用于选择一个内容源; 视频接收选择部分（11c），用于（i）识别连接到所选择的一个内容源的视频发送装置，以及（ii）使无线LAN模块（12a）从所识别的视频发送装置接收视频信号; 以及用于指示所识别的视频发送装置从所选择的一个内容源发送视频信号的内容切换指示部分（11d）。

公开(公告)号：US08234673B2

公开(公告)日：2012-07-31

申请号：US10542290

申请日：2004-01-05

申请人： Takuya Kinoshita ,  Ryota Yagi ,  Hiroyuki Nakaoka ,  Satoshi Terada ,  Toru Ueda

发明人： Takuya Kinoshita ,  Ryota Yagi ,  Hiroyuki Nakaoka ,  Satoshi Terada ,  Toru Ueda

IPC分类号： H04N5/445

CPC分类号： H04N21/4722 ,  H04N21/232 ,  H04N21/2393 ,  H04N21/25866 ,  H04N21/26283 ,  H04N21/4221 ,  H04N21/42222 ,  H04N21/4316 ,  H04N21/4622 ,  H04N21/47214 ,  H04N21/4782 ,  H04N21/482 ,  H04N21/6581 ,  H04N21/812 ,  H04N21/8133 ,  H04N21/8405 ,  H04N21/8586

摘要： An information server apparatus 116 includes a communication portion 118 receiving a request for getting information including a set of information source specifying information and time specifying information from a client, a user request information analyzing portion 122 and a table reference portion 129 analyzing the request for getting information and selecting information to be transmitted to the client terminal apparatus based on the result of analysis. Further, communication portion 118 returns the selected information to the client.

摘要翻译： 信息服务器装置116包括通信部118，其从客户端接收到获取包括一组信息源指定信息和时间指定信息的信息的请求，用户请求信息分析部分122和分析请求获得的表参考部分129 基于分析结果的信息和选择要发送给客户终端装置的信息。 此外，通信部分118将所选择的信息返回给客户端。