Fujitsu Corporation

Koji Maruhashi

Ken Kobayashi

Nobuhiro Yugami

Hiroshi Yamakawa

Hiroya Inakoshi

Yuhei Umeda

Yoshio Nakao

Masahiro Asaoka

Ryo Ochitani

Keisuke Goto

Tatsuru Matsuo

Nobuo Watanabe

Takuya Nishino

Masaru Todoriki

Yusuke Oki

Shotaro Yano

An apparatus identifies partial tensor data that contributes to machine learning using tensor data in a tensor format obtained by transforming training data having a graph structure. Based on the partial tensor data and the training data, the apparatus generates expanded training data to be used in the machine learning by expanding the training data.

Generation of expanded training data contributing to machine learning for relationship data

A machine learning apparatus calculates second values, based on first values each assigned to one variable value of each term in relation to a neuron in a layer following an input layer of a neural network, where the second values are assigned to variable-value combination patterns in relation to each following-layer neuron. Each second value is represented by a product of first values each assigned to a variable value included in the combination pattern in relation to the following-layer neuron. The apparatus then applies the second values as weights each to a numerical value when it is entered to the corresponding following-layer neuron, to calculate an output value of the neural network with the numerical values arranged in an input order. The apparatus updates reference values in a reference pattern and the first values based on input error that the output value exhibits with respect to training data.

Method and apparatus for machine learning

A learning method implemented by a computer, includes: creating an input data tensor including a local dimension and a universal dimension by partitioning series data into local units, the series data including a plurality of elements, each of the plurality of elements in the series data being logically arranged in a predetermined order; and performing machine learning by using tensor transformation in which a transformation data tensor obtained by transforming the input data tensor with a transformation matrix is outputted using a neural network, wherein the learning includes rearranging the transformation matrix so as to maximize a similarity to a matching pattern serving as a reference in the tensor transformation regarding the universal dimension of the input data tensor, and updating the matching pattern in a process of the machine learning regarding the local dimension of the input data tensor.

Learning method, learning apparatus, and non-transitory computer-readable storage medium for storing learning program

A non-transitory computer-readable recording medium stores therein a learning data selection program that causes a computer to execute a process including: extracting a first input data group relating to first input data in correspondence with designation of the first input data included in an input data group input to a machine learning model, the machine learning model classifying or determining transformed data that is transformed from input data; acquiring a first transformed data group of the machine learning model and a first output data group of the machine learning model, respectively, the first transformed data group being input to the machine learning model and corresponding to the first input data group, the first output data group corresponding to the first transformed data group; and selecting learning target data of an estimation model from the first input data group.

Learning data selection method, learning data selection device, and computer-readable recording medium

A learning method includes: acquiring input data and correct answer information, the input data including a set of multiple pieces of relationship data in which relationships between variables are recorded respectively; determining conversion rule corresponding to each of the multiple pieces of relationship data such that relationships before and after a conversion of a common variable commonly in the multiple pieces of relationship data are the same, when converting a variable value in each of the multiple pieces of relationship data into converted data rearranging the variable values in an order of input; converting each of the multiple pieces of relationship data into a multiple pieces of the converted data according to each corresponding conversion rule; and inputting a set of the multiple pieces of converted data to the neural network and causing the neural network to learn a learning model based on the correct answer information.

Computer-readable recording medium having stored therein learning program, learning method, and learning apparatus

A machine learning apparatus determines an order in which numerical values in an input dataset are to be entered to a neural network for data classification, based on a reference pattern that includes an array of reference values to provide a criterion for ordering the numerical values. The machine learning apparatus then calculates an output value of the neural network whose input-layer neural units respectively receive the numerical values arranged in the determined order. The machine learning apparatus further calculates an input error at the input-layer neural units, based on a difference between the calculated output value and a correct classification result indicated by a training label. The machine learning apparatus updates the reference values in the reference pattern, based on the input error at the input-layer neural units.

A data transformation apparatus selects items one by one and generates a first weight dataset and a second weight dataset on the basis of similarity between first records in a first dataset and second records in a second datasets. The first records and second records respectively include first item values and second item values that belong to the selected item. Based on the first weight dataset, the data transformation apparatus transforms the first dataset into a first similarity-determining dataset including third records. Each third record includes a numerical value that indicates a relationship between transformed item values belonging to different items. Further, based on the second weight dataset, the data transformation apparatus transforms the second dataset into a second similarity-determining dataset including fourth records. Each fourth record includes a numerical value that indicates a relationship between transformed item values belonging to different items.

Method and apparatus for transforming data

A classification method executed by a computer for classifying a plurality of records into a plurality of groups, the classification method includes: acquiring the plurality of records, the plurality of records including a variable value respectively; tentatively classifying the plurality of records into the plurality of groups; calculating a commonality value indicating a degree of commonality of the variable value among the plurality of groups, based on the variable value included in each of the tentatively classified groups; classifying the plurality of records into the plurality of groups based on the commonality value; and outputting a result of the classifying.

Classification device and classification method

A computer generates connection matrixes corresponding to subgraphs extracted from source graphs. The connection matrixes include a plurality of elements each describing a connection between nodes in a corresponding subgraph or between a node in the corresponding subgraph and a neighboring node connected to one of the nodes in the corresponding subgraph. Based on the connection matrixes, the computer then generates a reference matrix that indicates a characteristic pattern of connections of nodes in the subgraphs, taking into consideration an order in which these nodes are arranged. The computer further performs a node-ordering swap operation on individual subgraphs, such that a submatrix representing node-to-node connections in a subgraph will be more similar to the reference matrix. The node-ordering swap operation includes changing the order of two nodes in a subgraph or swapping one node in a subgraph with a neighboring node connected to that subgraph.

Method for processing graphs and information processing apparatus

An information processing device including: a storage unit configured to store a first record set including variables of multiple types, and a second record set different from the first record set and including variables of the multiple types; and a processing unit configured to calculate an expected value at which a first variable set representing a combination of variables formed by selecting one variable for each type in the first record set is expected to appear in the second record set, extract the first variable set based on the expected value and the number of records including the first variable set in the second record set, and output at least one of the extracted first variable set and a second variable set, the second variable set representing a combination of variables formed by selecting one or more variables for each type in the second record set.

Information processing device and information processing method

A computing unit obtains a graph including nodes and edges and representing a communication condition at first timing and at second timing and detects an edge that is added between the first and second timing among the edges. The computing unit calculates probabilities of transmitting information from each node to nodes coupled to the added edge, selects a subset of the nodes based on the calculated probabilities, selects nodes included in the subset as the starting points of information, calculates first probabilities of transmitting information from the selected nodes to each node based on the graph obtained at the first timing and second probabilities of transmitting information from the selected nodes to each node based on the graph obtained at the second timing, and detects a change in the communication condition between the first and second timing by comparing the first probabilities with the second probabilities.

Communication condition between entities detection displaying at least partial graphs indicating a location where a detected change occurred

In an information processing apparatus, a first deletion unit deletes, from sets stored in a storage unit, sets having less than a threshold number of included elements and elements existing in only sets whose number is less than a threshold number of occurrences. A grouping unit generates a group of sets associated with each other in terms of commonality of elements out of the sets remaining in the storage unit. A second deletion unit deletes, with respect to each generated group, sets having less than the threshold number of included elements and elements existing in only sets whose number is less than the threshold number of occurrences, from the sets belonging to the group. An output unit outputs a list of elements included in the sets remaining in each group where there are no sets or elements that need to be deleted.

Information processing apparatus and element extraction method

An entrustee information transmitting method includes an entrustment managing storage storing entrustment relationship information indicating correspondence between entrusters who are voters performing entrustment and entrustees who are voters entrusted by the entrusters in an entrustment managing storage unit; an attendance managing storage storing attendance information of respective voters in an attendance managing storage unit in units of bills; an indirect-entrustment voter extracting operation of extracting one or more indirect-entrustment voter who indirectly entrust an attendee by using the entrustment relationship information and the attendance information; an entrustee determining operation of determining attendees who are indirectly entrusted by the indirect-entrustment voters to be recommended entrustees; and an entrustee information transmitting operation of transmitting information of the recommended entrustees.

Entrustee information transmitting apparatus, entrustee information transmitting method and computer readable medium having a program implementing same

Detailed information of each analysis subject partial network is displayed on a left pane of a screen. The detailed information includes the number of nodes, the number of edges, and accumulative coverage of the analysis subject partial network for each disease. Based on the detailed information, a user can designate the analysis subject partial network of a disease the user wishes to analyze. When the user has designated the disease, a network diagram indicating a partial network related to the designated disease is displayed on a right pane.

Growing community of inventors

Hachioji, Japan

Koji Maruhashi