公开(公告)号：US09104980B2

公开(公告)日：2015-08-11

申请号：US13429130

申请日：2012-03-23

申请人： Kuniaki Noda ,  Takashi Hasuo ,  Kenta Kawamoto ,  Kohtaro Sabe

发明人： Kuniaki Noda ,  Takashi Hasuo ,  Kenta Kawamoto ,  Kohtaro Sabe

IPC分类号： G06K9/00 ,  G06N99/00

CPC分类号： G06N99/005

摘要： An information processing device includes a learning unit that performs, using an action performed by an object and an observation value of an image as learning data, learning of a separation learning model that includes a background model that is a model of the background of the image and one or more foreground model(s) that is a model of a foreground of the image, which can move on the background, in which the background model includes a background appearance model indicating the appearance of the background, and at least one among the one or more foreground model(s) includes a transition probability, with which a state corresponding to the position of the foreground on the background is transitioned by an action performed by the object corresponding to the foreground, for each action, and a foreground appearance model indicating the appearance of the foreground.

摘要翻译： 信息处理装置包括：学习单元，其使用由对象执行的动作和图像的观察值作为学习数据;学习包括作为图像的背景的模型的背景模型的分离学习模型; 以及一个或多个前景模型，其是可以在背景上移动的图像的前景的模型，其中背景模型包括指示背景的外观的背景外观模型，以及至少一个背景模型 一个或多个前景模型包括转移概率，对于每个动作，通过由对应于前景的对象执行的动作来转换对应于背景上的前景的位置的状态，以及前景外观模型 指示前景的外观。

公开(公告)号：US08527434B2

公开(公告)日：2013-09-03

申请号：US12791275

申请日：2010-06-01

申请人： Kuniaki Noda ,  Kohtaro Sabe ,  Yukiko Yoshiike ,  Kenta Kawamoto ,  Kenichi Hidai

发明人： Kuniaki Noda ,  Kohtaro Sabe ,  Yukiko Yoshiike ,  Kenta Kawamoto ,  Kenichi Hidai

IPC分类号： G06N5/00

CPC分类号： G06N3/006 ,  G06K9/00335 ,  G06K9/00664 ,  G06K9/6297

摘要： An information processing device includes: a learning section configured to learn a state transition probability model defined by state transition probability for each action of a state making a state transition due to an action performed by an agent capable of performing action and observation probability of a predetermined observed value being observed from the state, using an action performed by the agent and an observed value observed in the agent when the agent has performed the action.

摘要翻译： 一种信息处理装置，包括：学习部，其被配置为：由于能够执行动作的代理和所述预定的行为的观察概率而进行的状态转换的状态的每个动作，学习由状态转移概率定义的状态转移概率模型 观察到的值是从状态观察到的，使用由试剂进行的作用和在试剂进行作用时在试剂中观察到的观察值。

公开(公告)号：US08725510B2

公开(公告)日：2014-05-13

申请号：US12829984

申请日：2010-07-02

申请人： Yukiko Yoshiike ,  Kenta Kawamoto ,  Kuniaki Noda ,  Kohtaro Sabe

发明人： Yukiko Yoshiike ,  Kenta Kawamoto ,  Kuniaki Noda ,  Kohtaro Sabe

IPC分类号： G10L15/14

CPC分类号： G06N99/005

摘要： An HMM (Hidden Markov Model) learning device includes: a learning unit for learning a state transition probability as the function of actions that an agent can execute, with learning with HMM performed based on actions that the agent has executed, and time series information made up of an observation signal; and a storage unit for storing learning results by the learning unit as internal model data including a state-transition probability table and an observation probability table; with the learning unit calculating frequency variables used for estimation calculation of HMM state-transition and HMM observation probabilities; with the storage unit holding the frequency variables corresponding to each of state-transition probabilities and each of observation probabilities respectively, of the state-transition probability table; and with the learning unit using the frequency variables held by the storage unit to perform learning, and estimating the state-transition probability and the observation probability based on the frequency variables.

摘要翻译： HMM（隐马尔可夫模型）学习装置包括：用于学习作为代理可以执行的动作的函数的状态转移概率的学习单元，基于代理已经执行的动作执行的HMM的学习以及作出的时间序列信息 观察信号; 以及存储单元，用于将所述学习单元的学习结果存储为包括状态转换概率表和观察概率表的内部模型数据; 学习单元计算用于HMM状态转换和HMM观察概率的估计计算的频率变量; 存储单元保持状态转移概率表中分别对应于状态转换概率和每个观察概率的频率变量; 并且所述学习单元使用由所述存储单元保持的频率变量来执行学习，并且基于所述频率变量来估计所述状态转换概率和观察概率。

公开(公告)号：US20110010176A1

公开(公告)日：2011-01-13

申请号：US12829984

申请日：2010-07-02

申请人： Yukiko YOSHIIKE ,  Kenta Kawamoto ,  Kuniaki Noda ,  Kohtaro Sabe

发明人： Yukiko YOSHIIKE ,  Kenta Kawamoto ,  Kuniaki Noda ,  Kohtaro Sabe

IPC分类号： G10L15/14

CPC分类号： G06N99/005

摘要： An HMM (Hidden Markov Model) learning device includes: a learning unit for learning a state transition probability as the function of actions that an agent can execute, with learning with HMM performed based on actions that the agent has executed, and time series information made up of an observation signal; and a storage unit for storing learning results by the learning unit as internal model data including a state-transition probability table and an observation probability table; with the learning unit calculating frequency variables used for estimation calculation of HMM state-transition and HMM observation probabilities; with the storage unit holding the frequency variables corresponding to each of state-transition probabilities and each of observation probabilities respectively, of the state-transition probability table; and with the learning unit using the frequency variables held by the storage unit to perform learning, and estimating the state-transition probability and the observation probability based on the frequency variables.

摘要翻译： HMM（隐马尔可夫模型）学习装置包括：用于学习作为代理可以执行的动作的函数的状态转移概率的学习单元，基于代理已经执行的动作执行的HMM的学习以及作出的时间序列信息 观察信号; 以及存储单元，用于将所述学习单元的学习结果存储为包括状态转换概率表和观察概率表的内部模型数据; 学习单元计算用于HMM状态转换和HMM观察概率的估计计算的频率变量; 存储单元保持状态转移概率表中分别对应于状态转换概率和每个观察概率的频率变量; 并且所述学习单元使用由所述存储单元保持的频率变量来执行学习，并且基于所述频率变量来估计所述状态转换概率和观察概率。

公开(公告)号：US20100318478A1

公开(公告)日：2010-12-16

申请号：US12791240

申请日：2010-06-01

申请人： Yukiko Yoshiike ,  Kenta Kawamoto ,  Kuniaki Noda ,  Kohtaro Sabe

发明人： Yukiko Yoshiike ,  Kenta Kawamoto ,  Kuniaki Noda ,  Kohtaro Sabe

IPC分类号： G06N5/02 ,  G06F15/18

CPC分类号： G06N3/006 ,  G06K9/00335 ,  G06K9/00664 ,  G06K9/6297

摘要： An information processing device includes: a calculating unit configured to calculate a current-state series candidate that is a state series for an agent capable of actions reaching the current state, based on a state transition probability model obtained by performing learning of the state transition probability model stipulated by a state transition probability that a state will be transitioned according to each of actions performed by an agent capable of actions, and an observation probability that a predetermined observation value will be observed from the state, using an action performed by the agent, and an observation value observed at the agent when the agent performs an action; and a determining unit configured to determine an action to be performed next by the agent using the current-state series candidate in accordance with a predetermined strategy.

摘要翻译： 一种信息处理设备，包括：计算单元，被配置为基于通过执行状态转移概率的学习获得的状态转移概率模型来计算作为达到当前状态的动作的代理的状态序列的当前状态序列候选 由状态转移概率规定的模式，其状态将根据由能够执行动作的代理执行的动作而转变，并且使用由代理执行的动作从该状态观察到预定观察值的观察概率， 以及当代理人执行动作时在代理处观察到的观察值; 以及确定单元，被配置为根据预定策略来确定所述代理使用所述当前状态序列候选来执行的动作。

公开(公告)号：US07783585B2

公开(公告)日：2010-08-24

申请号：US11697238

申请日：2007-04-05

申请人： Kohtaro Sabe ,  Kazumi Aoyama ,  Jun Yokono ,  Kenichi Hidai ,  Kuniaki Noda

发明人： Kohtaro Sabe ,  Kazumi Aoyama ,  Jun Yokono ,  Kenichi Hidai ,  Kuniaki Noda

IPC分类号： G06E1/00 ,  G06E3/00 ,  G06F15/18 ,  G06G7/00

CPC分类号： G06F15/18 ,  G06N3/0454 ,  G06N3/088

摘要： A data processing device for processing time-sequence data includes a learning unit for performing self-organizing learning of a SOM (self-organization map) making up a hierarchical SOM in which a plurality of SOMs are connected so as to construct a hierarchical structure, using, as SOM input data which is input to the SOM, a time-sequence of node information representing a winning node of a lower-order SOM which is at a lower hierarchical level from the SOM.

摘要翻译： 一种用于处理时间序列数据的数据处理装置，包括：学习单元，用于执行构成其中连接有多个SOM的层次化SOM的SOM（自组织图）的自组织学习，以构建层次结构， 使用作为输入到SOM的SOM输入数据，表示代表来自SOM的较低层级的低阶SOM的获胜节点的节点信息的时间序列。

公开(公告)号：US20070250461A1

公开(公告)日：2007-10-25

申请号：US11697238

申请日：2007-04-05

申请人： Kohtaro Sabe ,  Kazumi Aoyama ,  Jun Yokono ,  Kenichi Hidai ,  Kuniaki Noda

发明人： Kohtaro Sabe ,  Kazumi Aoyama ,  Jun Yokono ,  Kenichi Hidai ,  Kuniaki Noda

IPC分类号： G06F15/18

CPC分类号： G06F15/18 ,  G06N3/0454 ,  G06N3/088

摘要： A data processing device for processing time-sequence data includes a learning unit for performing self-organizing learning of a SOM (self-organization map) making up a hierarchical SOM in which a plurality of SOMs are connected so as to construct a hierarchical structure, using, as SOM input data which is input to the SOM, a time-sequence of node information representing a winning node of a lower-order SOM which is at a lower hierarchical level from the SOM.

摘要翻译： 一种用于处理时间序列数据的数据处理装置，包括：学习单元，用于执行构成其中连接有多个SOM的层次化SOM的SOM（自组织图）的自组织学习，以构建层次结构， 使用作为输入到SOM的SOM输入数据，表示代表来自SOM的较低层级的低阶SOM的获胜节点的节点信息的时间序列。

公开(公告)号：US20090299933A1

公开(公告)日：2009-12-03

申请号：US12413004

申请日：2009-03-27

申请人： Kazumi Aoyama ,  Masato Ito ,  Kuniaki Noda

发明人： Kazumi Aoyama ,  Masato Ito ,  Kuniaki Noda

IPC分类号： G06N5/02 ,  G06F15/18

CPC分类号： G06N3/049

摘要： A data processing apparatus includes: predicting means for calculating a prediction value of time series data with respect to input of the time series data using a prediction model for predicting the time series data; determining means for determining a target value of the time series data on the basis of the prediction value of the time series data; error calculating means for calculating an error of the prediction value relative to the target value; and retrieving means for retrieving error reduction data as input of the time series data to the prediction model for reducing the error of the prediction value.

摘要翻译： 数据处理装置包括：预测装置，用于使用用于预测时间序列数据的预测模型来计算关于时间序列数据的输入的时间序列数据的预测值; 确定装置，用于根据时间序列数据的预测值确定时间序列数据的目标值; 误差计算装置，用于计算预测值相对于目标值的误差; 以及检索装置，用于将所述时间序列数据的输入作为输入的误差减少数据提取到所述预测模型，以减少所述预测值的误差。

公开(公告)号：US20090157634A1

公开(公告)日：2009-06-18

申请号：US12335127

申请日：2008-12-15

申请人： Masato ITO ,  Kenichi Hidai ,  Katsuki Minamino ,  Kuniaki Noda

发明人： Masato ITO ,  Kenichi Hidai ,  Katsuki Minamino ,  Kuniaki Noda

IPC分类号： G06F7/06 ,  G06F17/30

CPC分类号： G06F17/30864

摘要： An information processing device includes an obtaining unit to obtain two pieces of information that are targets for searching for connections; a connection searching unit to use an action model wherein the manner of obtaining, from input information, obtain related information that relates to the input information is modeled, and find connection information to connect the two pieces of information, thereby searching connections between the two pieces of information; and a search result output unit to output the search results of the connections between the two pieces of information.

摘要翻译： 信息处理装置包括获取单元，用于获得作为搜索连接的目标的两条信息; 连接搜索单元，用于使用动作模型，其中从输入信息获得与获取与输入信息相关的相关信息的方式被建模，并且找到连接信息以连接两条信息，从而搜索两个部分之间的连接 的信息; 以及搜索结果输出单元，输出两条信息之间的连接的搜索结果。

公开(公告)号：US20100010943A1

公开(公告)日：2010-01-14

申请号：US12494593

申请日：2009-06-30

申请人： Masato ITO ,  Kazumi Aoyama ,  Kuniaki Noda

发明人： Masato ITO ,  Kazumi Aoyama ,  Kuniaki Noda

IPC分类号： G06F15/18

CPC分类号： G06N3/08 ,  G06N3/0454

摘要： A learning device includes: a plurality of learning modules, each of which performs update learning to update a plurality of model parameters of a pattern learning model that learns a pattern using input data; model parameter sharing means for causing two or more learning modules from among the plurality of learning modules to share the model parameters; module creating means for creating a new learning module corresponding to new learning data for learning the pattern when the new learning data are supplied as the input data; similarity evaluation means for evaluating similarities among the learning modules after the update learning is performed over all the learning modules including the new learning module; and module integrating means for determining whether to integrate the learning modules on the basis of the similarities among the learning modules and integrating the learning modules.

摘要翻译： 学习装置包括：多个学习模块，每个学习模块执行更新学习以更新使用输入数据学习模式的模式学习模型的多个模型参数; 模型参数共享装置，用于使所述多个学习模块中的两个或更多学习模块共享所述模型参数; 模块创建装置，用于当提供新的学习数据作为输入数据时创建对应于用于学习图案的新学习数据的新学习模块; 在包括新的学习模块的所有学习模块执行更新学习之后，评估学习模块之间的相似度的相似度评估装置; 以及模块集成装置，用于基于学习模块之间的相似度来确定是否集成学习模块，并且集成学习模块。