International Business Machines Corporation

Kabushiki Kaisha Toshiba

Nitto Chemical Industry Co., Ltd.

Ntt Electronics Corporation

Nitto Kagaku Kogyo Kabushiki Kaisha

Takeshi Inagaki

Aya Minami

Koichi Sato

Masaki Hirose

Shinsuke Mitsuma

Kazuhiro Tsuruta

Tadashi Kojima

Norie Iwasaki

Terue Watanabe

Yasuhiro Hayashi

Shuji Abe

Toshihiko Kaneshige

Yohichi Miwa

Shinobu Fujihara

Jun Inagawa

Tomio Nakamura

Yasuhiro Hori

Kouichi Kurihara

Meisei Nishikawa

Kiyonobu Niwa

Takeyuki Fujita

Shinji Yoda

Takeshi Yoshida

Yoshiro Ashina

Katsumi Nakamura

Tuyoshi Irie

Katsuhito Toyoda

Yuko Nikaido

Denzi Sato

Katsuaki Kikuchi

A method, computer program product and system for generating a neural network. Initial neural networks are prepared, each of which includes an input layer containing one or more input nodes, a middle layer containing one or more middle nodes, and an output layer containing one or more output nodes. A new neural network is generated that includes a new middle layer containing one or more middle nodes based on the middle nodes of the middle layers of the initial neural networks.

Generation of neural network containing middle layer background

Methods, apparatus, and products for creating an executable process from a text description written in a natural language in accordance with the present invention are described. A set of propositions is extracted from a text document written in a natural language. Based on the set extracted of propositions, a set of formulas is extracted from the text document. A state transition graph comprising a set of proposition value determination paths constrained by the set of formulas is then created. The state transition graph is translated into a software application.

Creating an executable process from a text description written in a natural language

A computer-implemented method according to one embodiment includes receiving a single instance of training data, simplifying the single instance of training data to create a single instance of simplified training data, generating a plurality of training data variants, based on the single instance of simplified training data, and training a machine learning model, utilizing the plurality of training data variants.

Adjusting training data for a machine learning processor

Embodiments of the present invention is a technique of searching for relevant nodes. This technique may include: in response to selection of a first node, displaying, as first relevant nodes, nodes having a first relevance of at least a predetermined value among nodes connected from the first node by two hops; and, in response to selection of at least one of the first relevant nodes, displaying the selected first relevant node as a second node involving the first node. This technique may further include displaying, as second relevant nodes, nodes having a second relevance of at least a predetermined value among nodes connected from the second node by two hops.

Method of searching for relevant node, and computer therefor and computer program

An apparatus supports acquisition of information from a document including a plurality of words. An acquisition hardware unit acquires first information that shows a degree to which the document belongs to each of a plurality of clusters based on a concept included in the document. Second information shows a degree to which a single word among the plurality of words appears in each of the plurality of clusters based on a concept of the single word. A generation hardware unit, based on the first and second information, generates third information that shows a degree of overlap between the concept included in the document and the concept of the single word. A determination hardware unit determines whether or not the third information shows a degree of overlap that is lower than a predetermined criterion, and an output hardware unit outputs a result of this determination.

Supporting acquisition of information

According to an aspect, there are provided an apparatus, a program for causing a computer to function as such an apparatus, and a method, wherein the apparatus includes a selection section for selecting a plurality of sample documents from a plurality of documents and a first parameter generation section for analyzing the plurality of sample documents to generate an initial parameter matrix expressing a probability that each of a plurality of words included in the plurality of sample documents is included in each of a plurality of topics. The apparatus also includes a second parameter generation section for analyzing the plurality of documents by using each value included in the initial parameter matrix as an initial value to generate a parameter matrix expressing a probability that each of a plurality of words included in the plurality of documents is included in each of a plurality of topics.

Apparatus for clustering a plurality of documents

Techniques provide for searching pieces of document data using a search keyword. The technique includes: calculating, as a first vector, respective first scores at which or respective probabilities that each of the pieces of document data belongs to clusters or classes; calculating, as a second vector, respective second scores at which or respective probabilities that the search keyword or a relevant keyword associated with the search keyword belongs to the clusters or the classes; calculating an inner product of each of the first vectors and the second vector, the calculated inner product being a third score of the corresponding piece of document data regarding the search keyword; and acquiring a correlation value from document data containing each keyword in a classification keyword set and document data with the third score that is equal to or more than a predetermined threshold or is included in a predetermined high-ranking proportion.

Method, computer system, and computer program for searching document data using search keyword

Processing for a time-series analysis of keywords comprises clustering or classifying pieces of document data, each of which is description of a phenomenon in a natural language, on the basis of frequencies of occurrence of keywords in the pieces of document data, individual keywords being also clustered or classified by clustering or classifying the pieces of document data, and performing a time-series analysis of frequencies of occurrence of pieces of document data containing individual keywords in clusters or classes into which the pieces of document data are clustered or classified or a time-series analysis of frequencies of occurrence of pieces of document data containing clusters or classes into which the individual keywords are clustered or classified. Frequency distribution showing variation of the frequencies of occurrence of the pieces of document data is acquired by the time-series analysis.

Time-series analysis of keywords

A control apparatus connected to different types of storage devices include a performance-information storing section that stores performance information on the storage devices; a list storing section that stores a list of data on the storage devices; a monitoring section that monitors the load statuses of the storage devices and the control apparatus; a detecting section; an estimating section; and a determining section.

Controlling replication of data among storage devices

A video signal synchronization signal generating apparatus for making a display reference synchronization signal Vb that serves as a reference of video display and has a first frequency and an input synchronization signal Vi that constitutes images and has a second frequency synchronized with each other, the apparatus including: a frequency ratio generating section configured to divide a frequency that is double the first frequency by the second frequency to calculate a frequency ratio n; a Vx generation comparator circuit section configured to generate coincidence signal Vx' having pulses that are inserted by equally dividing one period of the input synchronization signal Vi by the frequency ratio n; and a Vx generation circuit section configured to remove the alternate pulses of the coincidence signal Vx&#x2032; to generate synchronization signal Vx of a same phase as the phase of the input synchronization signal Vi.

Video signal synchronization signal generating apparatus and video signal synchronization signal generation method

Growing community of inventors

Sagamihara, Japan

Takeshi Inagaki