Abstract: An information processing apparatus includes a processor including hardware. The processor extracts neighboring nodes in two or more different extraction ranges for each node constituting input data of a graph structure. The processor calculates an anomaly score representing a degree of anomaly of the node for each extraction range based on a representation of a combination of the node and the neighboring nodes. The processor records each calculated anomaly score in a storage. The processor selects a maximum anomaly score among the anomaly scores recorded in the storage. The processor determines an anomaly node in the input data of the graph structure based on the selected maximum anomaly score. The processor outputs information of the anomaly node.

Abstract: According to one embodiment, a data processing apparatus includes a processor provided with hardware. The processor extracts a first event data item, a second event data item, and a third event data item from input first document data. When a first relational data item indicating a presence of transitivity between the first event data item and the second event data item is extracted and a second relational data item indicating a presence of transitivity between the second event data item and the third event data item is extracted, the processor generates a third relational data item indicating a presence of a relation between the first event data item and the third event data item.

Abstract: According to one embodiment, a learning apparatus includes a processor. The processor performs, on a neural network model, an adaptation processing that includes at least either insertion of an activation function, or correction of the activation function. The processor generates a trained model by training the neural network model on which the adaptation processing has been performed. The processor performs pruning on the trained model to generate a reconstructed model from which a parameter has been reduced.

Abstract: According to one embodiment, a learning system includes a plurality of local devices and a server. Each of the local devices includes a processor. The processor selects a mini-batch from local data. The processor trains a local model using the mini-batch. The processor generates local data information relating to the local data included in the mini-batch and indicating information different from a label. The processor transmits a local model parameter relating to the local model and the local data information to the server. The server includes a processor. The processor calculates an integrated parameter using the local data information acquired from each of the local devices. The processor updates a global model using the integrated parameter and the local model parameter acquired from each of the local devices.

Abstract: A symbol sequence converting apparatus according to an embodiment includes one or more hardware processors. The processors: generates a plurality of candidate output symbol sequences, based on rule information in which input symbols are each associated with one or more output symbols each obtained by converting the corresponding input symbol in accordance with a predetermined conversion condition, the plurality of candidate output symbol sequences each containing one or more of the output symbols and corresponding to an input symbol sequence containing one or more of the input symbols; derives respective confidence levels of the plurality of candidate output symbol sequences by using a learning model; and identifies, as an output symbol sequence corresponding to the input symbol sequence, the candidate output symbol sequence corresponding to a highest confidence level.

Abstract: According to one embodiment, a learning apparatus includes a processor. The processor acquires a document to which a tag is added. The processor converts the document into an image to generate a document image, and converts the tag into an image according to composition of the document image to generate a tag image. The processor trains a network model using the document image as input data and the tag image as ground truth data to generate a trained model.

Abstract: In general, according to one embodiment, an information processing apparatus includes a processor. The processor includes hardware configured to extract a sub-graph that is a graph structure operating independently from data of an input graph structure including a plurality of nodes and an edge connecting the nodes, extract a path from the extracted sub-graph, and perform learning of an embedding model using the extracted path. The embedding model performs embedding on data of a graph structure.

Abstract: In general, according to one embodiment, an information processing apparatus includes a processor. The processor includes hardware configured to extract a sub-graph that is a graph structure operating independently from data of an input graph structure including a plurality of nodes and an edge connecting the nodes, extract a path from the extracted sub-graph, and perform learning of an embedding model using the extracted path. The embedding model performs embedding on data of a graph structure.

Abstract: An information processing apparatus includes a processor. The processor receives an input of a graph structure. The graph structure has nodes including text and edge. The processor assigns the nodes to one or more clusters. The processor partitions the text into words. The processor classifies the words into 1) a word representing a subject or target of an operation, 2) a word representing a content or state of the operation, and 3) other words. The processor extracts a frequent word by counting a frequency of occurrence of one or more words classified as the words representing the subject or target of the operation and extracts a frequent word by counting a frequency of occurrence of one or more words classified as the words representing the content or state of the operation, for the respective clusters.

Abstract: A learning device includes one or more processors. The processors input, to an input layer of a neural network including hidden layers defined for respective first arrangement patterns indicating arrangement of one or more words, and output layers connected with some of hidden layers, one or more first morphemes conforming to any of first arrangement patterns, among morphemes included in a document, and learn the neural network to minimize a difference between one or more second morphemes conforming to any of second arrangement patterns indicating arrangement of one or more words, among morphemes included in the document, and output morphemes from the neural network for the input first morphemes. The processors output an embedding vector of the first morphemes that is obtained based on a weight of the learned neural network.

Abstract: According to one embodiment, an information processing apparatus comprises a processor. The processor is configured to receive a first number of outputs from the first number of sensors mutually different in response to an odor, obtain a second number of indicators by using the first number of outputs from the first number of sensors, the second number being larger than the first number, obtain the second number of indicator values by using the first number of outputs and the second number of indicators, and discriminate the odor based on the second number of indicator values.

Abstract: According to one embodiment, a data processing apparatus includes a processor provided with hardware. The processor extracts a first event data item, a second event data item, and a third event data item from input first document data. When a first relational data item indicating a presence of transitivity between the first event data item and the second event data item is extracted and a second relational data item indicating a presence of transitivity between the second event data item and the third event data item is extracted, the processor generates a third relational data item indicating a presence of a relation between the first event data item and the third event data item.

Abstract: An information processing apparatus includes a processor. The processor receives an input of a graph structure. The graph structure has nodes including text and edge. The processor assigns the nodes to one or more clusters. The processor partitions the text into words. The processor classifies the words into 1) a word representing a subject or target of an operation, 2) a word representing a content or state of the operation, and 3) other words. The processor extracts a frequent word by counting a frequency of occurrence of one or more words classified as the words representing the subject or target of the operation and extracts a frequent word by counting a frequency of occurrence of one or more words classified as the words representing the content or state of the operation, for the respective clusters.

Abstract: A symbol sequence converting apparatus according to an embodiment includes one or more hardware processors. The processors: generates a plurality of candidate output symbol sequences, based on rule information in which input symbols are each associated with one or more output symbols each obtained by converting the corresponding input symbol in accordance with a predetermined conversion condition, the plurality of candidate output symbol sequences each containing one or more of the output symbols and corresponding to an input symbol sequence containing one or more of the input symbols; derives respective confidence levels of the plurality of candidate output symbol sequences by using a learning model; and identifies, as an output symbol sequence corresponding to the input symbol sequence, the candidate output symbol sequence corresponding to a highest confidence level.

Abstract: According to one embodiment, an information processing apparatus comprises a processor. The processor is configured to receive a first number of outputs from the first number of sensors mutually different in response to an odor, obtain a second number of indicators by using the first number of outputs from the first number of sensors, the second number being larger than the first number, obtain the second number of indicator values by using the first number of outputs and the second number of indicators, and discriminate the odor based on the second number of indicator values.

Abstract: A learning device includes one or more processors. The processors input, to an input layer of a neural network including hidden layers defined for respective first arrangement patterns indicating arrangement of one or more words, and output layers connected with some of hidden layers, one or more first morphemes conforming to any of first arrangement patterns, among morphemes included in a document, and learn the neural network to minimize a difference between one or more second morphemes conforming to any of second arrangement patterns indicating arrangement of one or more words, among morphemes included in the document, and output morphemes from the neural network for the input first morphemes. The processors output an embedding vector of the first morphemes that is obtained based on a weight of the learned neural network.

Abstract: According to an embodiment, an image processing apparatus includes an acquirer, first and second calculators, and a selector. The acquirer acquires a first image of an object captured in a first imaging direction and a second image of the object captured in a second imaging direction. The first calculator calculates, for each pixel included in the respective first and second images, likelihood of whether the pixel is included in a region of the object on the basis of feature information indicating image feature. The second calculator calculates, on the basis of the likelihood, a degree of similarity between a region of interest in the first image and a candidate region in the second image. The candidate region is a candidate of a corresponding region corresponding to the region of interest. The selector selects the candidate region serving as the corresponding region on the basis of the degree of similarity.

Abstract: A medical image diagnosis system according to an embodiment includes a determining unit, a rendering processing unit, and an output unit. The determining unit is configured to, based on information related to a stereoscopic function of a display unit connected to an output target apparatus serving as an output target, determine a parallax image number of images that are for realizing a stereoscopic view and are to be displayed by the display unit. The rendering processing unit is configured to generate rendering images corresponding to the parallax image number, by performing a rendering process on volume data that represents three-dimensional medical images. The output unit is configured to output the rendering images corresponding to the parallax image number to the output target apparatus, as the images that are for realizing the stereoscopic view and are to be simultaneously displayed by the display unit.

Abstract: According to one embodiment, a display device includes a display unit, an optical unit, and a reflector. The display unit includes a plurality of pixels arranged in a first plane. The display unit emits light including image information. At least a portion of the light emitted by the display unit is incident on the optical unit. The optical unit includes a first optical element. A travel direction of the at least the portion of the light is modified by the first optical element. The reflector reflects the at least the portion of the light modified by the first optical element. A perpendicular direction perpendicular to the first plane is non-parallel to an optical axis of the first optical element.

Abstract: According to one embodiment, a display includes a projector, a first optical unit, and a second optical unit. The projector emits a first light including image information. The first optical unit transmits at least a portion of a second light. The second optical unit reflects at least a portion of the first light and transmits at least a portion of the second light. A light reflectance of the first optical unit is lower than a light reflectance of the second optical unit, and a light absorptance of the first optical unit is higher than a light absorptance of the second optical unit.