公开(公告)号：US20150088804A1

公开(公告)日：2015-03-26

申请号：US14563227

申请日：2014-12-08

Applicant: NEC CORPORATION

Inventor： Riki ETO ,  Ryohei FUJIMAKI ,  Satoshi MORINAGA

IPC: G06N7/00

CPC classification number: G06N7/005 ,  G06F17/18 ,  G06K9/00536 ,  G06N5/02 ,  G06N5/025

Abstract: A hierarchical latent structure setting unit 81 sets a hierarchical latent structure that is a structure in which latent variables are represented by a tree structure and components representing probability models are located at nodes of a lowest level of the tree structure. A variational probability computation unit 82 computes a variational probability of a path latent variable that is a latent variable included in a path linking a root node to a target node in the hierarchical latent structure. A component optimization unit 83 optimizes each of the components for the computed variational probability. A gating function optimization unit 84 optimizes a gating function model that is a model for determining a branch direction according to the multivariate data in a node of the hierarchical latent structure, on the basis of the variational probability of the latent variable in the node.

Abstract translation: 分层潜在结构设置单元81设置作为其中潜变量由树结构表示的结构的分层潜在结构，并且表示概率模型的分量位于树结构的最底层的节点处。 变分概率计算单元82计算作为潜在变量的路径潜变量的变分概率，所述潜变量包括在将根节点链接到分层潜在结构中的目标节点的路径中。 分量优化单元83针对所计算的变分概率优化每个分量。 门控功能优化单元84基于节点中的潜在变量的变分概率来优化门控功能模型，门控功能模型是根据层级潜在结构的节点中的多变量数据确定分支方向的模型。

公开(公告)号：US20150088789A1

公开(公告)日：2015-03-26

申请号：US14032295

申请日：2013-09-20

Applicant: NEC Corporation

Inventor： Yosuke MOTOHASHI ,  Satoshi MORINAGA ,  Ryohei FUJIMAKI ,  Riki ETO

IPC: G06N5/02 ,  G06N99/00

CPC classification number: G06N5/02 ,  G06N7/005 ,  G06N99/005

Abstract: A hierarchical latent structure setting unit 81 sets a hierarchical latent structure that is a structure in which latent variables are represented by a tree structure and components representing probability models are located at nodes of a lowest level of the tree structure. A variational probability computation unit 82 computes a variational probability of a path latent variable that is a latent variable included in a path linking a root node to a target node in the hierarchical latent structure. A component optimization unit 83 optimizes each of the components for the computed variational probability. A gating function optimization unit 84 optimizes a gating function model that is a model for determining a branch direction according to the multivariate data in a node of the hierarchical latent structure, based on the variational probability of the latent variable in the node.

Abstract translation: 分层潜在结构设置单元81设置作为其中潜变量由树结构表示的结构的分层潜在结构，并且表示概率模型的分量位于树结构的最底层的节点处。 变分概率计算单元82计算作为潜在变量的路径潜变量的变分概率，所述潜变量包括在将根节点链接到分层潜在结构中的目标节点的路径中。 分量优化单元83针对所计算的变分概率优化每个分量。 门控功能优化单元84基于节点中的潜在变量的变分概率来优化门控功能模型，门控功能模型是根据层级潜在结构的节点中的多变量数据确定分支方向的模型。

公开(公告)号：US20140236871A1

公开(公告)日：2014-08-21

申请号：US14164784

申请日：2014-01-27

Applicant: NEC Corporation

Inventor： Ryohei FUJIMAKI ,  Ji LIU

IPC: G06N99/00

CPC classification number: G06N99/005

Abstract: A gradient computation unit computes a gradient of an objective function in a variable to be optimized. An added variable selection unit adds a variable corresponding to a largest absolute value of the computed gradient from among variables included in a variable set, to a nonzero variable set. A variable optimization unit optimizes a value of the variable to be optimized, for each variable included in the nonzero variable set. A deleted variable selection unit deletes a variable that, when deleted, causes a smallest increase of the objective function from among variables included in the nonzero variable set, from the nonzero variable set. An objective function evaluation unit computes a value of the objective function for the variable to be optimized.

Abstract translation: 梯度计算单元计算要优化的变量中的目标函数的梯度。 添加的变量选择单元将包括在变量集合中的变量中的与计算出的梯度的最大绝对值相对应的变量添加到非零变量集。 变量优化单元针对包含在非零变量集中的每个变量优化要优化的变量的值。 删除的变量选择单元删除一个变量，该变量当被删除时从非零变量集中引起非零变量集中包括的变量中的目标函数的最小增加。 目标函数评估单元计算要优化的变量的目标函数的值。

公开(公告)号：US20140236869A1

公开(公告)日：2014-08-21

申请号：US14167020

申请日：2014-01-29

Applicant: NEC CORPORATION

Inventor： Ryohei FUJIMAKI ,  Satoshi MORINAGA ,  Ji LIU ,  Yoshinobu KAWAHARA

IPC: G06N5/00

CPC classification number: G06N20/00

Abstract: An optimality degree computation unit computes an optimality degree in the case where a first variable included in a variable set is a candidate for an addition variable, using an objective function. An addition threshold computation unit computes an addition threshold based on the computed optimality degree, the addition threshold being a threshold of the optimality degree and indicating a criterion for determining whether or not the first variable is to be set as the candidate for the addition variable. An objective function value computation unit computes an objective function value which is a difference between a value of the objective function computed using variables to be optimized and a value of the objective function computed using the variables to be optimized from which a second variable included in a nonzero variable set is excluded.

Abstract translation: 在使用目标函数的变量集中包含的第一变量为加法变量的候补的情况下，最优度计算单元计算最优度度。 相加阈值计算单元基于所计算的最优度来计算加法阈值，所述相加阈值是所述最优度的阈值，并且指示用于确定所述第一变量是否被设置为所述加法变量的候选的准则。 目标函数值计算单元计算目标函数值，该目标函数值是使用要优化的变量计算的目标函数的值与使用要优化的变量计算的目标函数的值之间的差值， 非零变量集被排除。