Abstract: A non-transitory computer-readable recording medium storing a machine learning program for causing a computer to execute a process, the process includes inputting moving image data that includes at least a first frame image and a second frame image to a first machine learning model trained by using training data, and training an encoder by detecting a first object and a second object from the first frame image and the second frame image, respectively, based on an inference result by the first machine learning model, determining identity between the first object and the second object that have been detected, and inputting, to the encoder, first data in a first image area that includes the first object and second data in a second image area that includes the second object, the first object and the second object having been determined to have the identity.

Abstract: A non-transitory computer-readable recording medium stores a machine learning program causing a computer to execute a process including: calculating an average of latent variables by inputting input data to an encoder; sampling a noise, based on a probability distribution of the noise, in which a probability is decreased as the probability approaches to a center of the probability distribution from a predetermined position in the probability distribution; calculating the latent variable by adding the noise to the average; calculating output data by inputting the calculated latent variable to a decoder; and training the encoder and the decoder in accordance with a loss function, the loss function including encoding information and an error between the input data and the output data, the encoding information being information of a probability distribution of the calculated latent variable and a prior distribution of the latent variable.

Abstract: A non-transitory computer-readable recording medium stores a machine learning program causing a computer to execute a process including: calculating an average and a variance of a latent variable by inputting input data to an encoder; sampling a noise based on a normal distribution of the variance; calculating the latent variable by adding the noise to the average; calculating output data by inputting the calculated latent variable to a decoder; and training the encoder and the decoder in accordance with a loss function, the loss function including a value and an error between the input data and the output data, the value being obtained by multiplying encoding information by a correction coefficient based on the noise, the encoding information being information of a probability distribution of the latent variable and a prior distribution of the latent variable.

Abstract: A non-transitory computer-readable recording medium stores a program for causing a computer to execute a process including for each of plural pieces of first-type training data including image information, first semantic information, and a first class of a relevant first object, generating a first hyperdimensional vector (HV) from the image information and the first semantic information, and storing the first HV in a storage unit in correlation with the first class, and for each of plural pieces of second-type training data including second semantic information and a second class of a relevant second object, obtaining, from the storage unit, a predetermined number of HVs exhibiting a higher degree of matching with an HV generated from the second semantic information, generating a second HV of the second-type training data based on the predetermined number of HVs, and storing the second HV in the storage unit in correlation with the second class.

Abstract: A computer includes: a memristor array including memristors arranged at intersections between word lines and a first bit line in the memristor array and at intersections between the word lines and second bit lines in the memristor array; an adder circuit configured to obtain sum voltages for the second bit lines by adding first voltages generated according to currents that flow in the second bit lines when a first pattern is supplied to the word lines to difference voltages between a reference voltage generated according to a current that flows in the first bit line when a second pattern is supplied to the word lines and second voltages generated according to currents that flow in the second bit lines when a second pattern is supplied to the word lines; and a detection circuit that detects a second bit line that corresponds to a maximum value of the sum voltages.

Abstract: A non-transitory computer-readable storage medium storing a database construction program that causes a computer to execute a process that includes analyzing an input image or text to generate a semantic representation including a plurality of subgraphs defining relationships between a plurality of first parts of speech and a plurality of second parts of speech; extracting, from a plurality of subgraphs stored in a database, third parts of speech having relationships with the first parts of speech included in the plurality of subgraphs of the semantic representation; generating first knowledge including a plurality of subgraphs in which the first parts of speech in the plurality of subgraphs of the semantic representation are replaced with the third parts of speech; and registering, in the database, a remaining subgraph obtained by removing a contradictory subgraph from the plurality of subgraphs included in the first knowledge based on the semantic representation and the database.

Abstract: A non-transitory computer-readable storage medium storing an output program that causes at least one computer to execute a process, the process includes converting input data into a semantic representation; and outputting a validity score based on a matching degree between a first relationship between a noun and a verb in the semantic representation and a second relationship between the noun and the verb in a database.

Abstract: A non-transitory computer-readable storage medium storing an inference program that causes at least one computer to execute a process, the process includes, training a neural network based on a plurality of pieces of first learning data that belongs to a first certain number of object classes and that does not include second learning data; generating a fully connected layer separated neural network by separating a fully connected layer of the neural network; generating a learning feature by using the fully connected layer separated neural network for each of a second certain number of pieces of the first learning data for each of the object classes; generating a class hyperdimensional vector for each of the object classes from each of the learning feature; and storing the class hyperdimensional vector in association with the object classes in a memory.

Abstract: A computer includes: a memristor array including memristors arranged at intersections between word lines and a first bit line in the memristor array and at intersections between the word lines and second bit lines in the memristor array; an adder circuit configured to obtain sum voltages for the second bit lines by adding first voltages generated according to currents that flow in the second bit lines when a first pattern is supplied to the word lines to difference voltages between a reference voltage generated according to a current that flows in the first bit line when a second pattern is supplied to the word lines and second voltages generated according to currents that flow in the second bit lines when a second pattern is supplied to the word lines; and a detection circuit that detects a second bit line that corresponds to a maximum value of the sum voltages.

Abstract: A non-transitory computer-readable recording medium stores a program for causing a computer to execute a process including for each of plural pieces of first-type training data including image information, first semantic information, and a first class of a relevant first object, generating a first hyperdimensional vector (HV) from the image information and the first semantic information, and storing the first HV in a storage unit in correlation with the first class, and for each of plural pieces of second-type training data including second semantic information and a second class of a relevant second object, obtaining, from the storage unit, a predetermined number of HVs exhibiting a higher degree of matching with an HV generated from the second semantic information, generating a second HV of the second-type training data based on the predetermined number of HVs, and storing the second HV in the storage unit in correlation with the second class.

Abstract: A non-transitory computer-readable recording medium storing an inference program for causing a computer to execute a process, the process including: extracting features of a piece of data by inputting the piece of data to a neural network; generating a hyperdimensional vector based on the extracted features; and storing the generated hyperdimensional vector in a storage unit with the hyperdimensional vector related to a label of the piece of data.

Abstract: An information providing method is an information providing method for consumer electronics devices, a display device, and a server, all of which are connected via a public network, the information providing method including: (a) receiving, by the server from the consumer electronics devices, information pieces on the consumer electronics devices; (b) filtering, by the server, the information pieces on the consumer electronics devices received in step (a), to obtain one or more filtered information pieces, and performing, by the server, processing for generating display information for display, by the display device, in a specific display format; and (c) transmitting, by the server, the display information generated in step (b) to the display device.

Abstract: An information sharing method that provides a graphical user interface image for sharing information relating to an appliance within a home among a plurality of users includes a receiving step of receiving, as home appliance event information, information on a state change of an appliance within a plurality of homes, a priority determining step of determining a priority of a home that is to be displayed in the graphical user interface image in accordance with an occurrence frequency of the home appliance event information within each home, and a home determining step of determining a home to be displayed in the graphical user interface image in accordance with the priority.

Abstract: An information providing method is an information providing method for consumer electronics devices, a display device, and a server, all of which are connected via a public network, the information providing method including: (a) receiving, by the server from the consumer electronics devices, information pieces on the consumer electronics devices; (b) filtering, by the server, the information pieces on the consumer electronics devices received in step (a), to obtain one or more filtered information pieces, and performing, by the server, processing for generating display information for display, by the display device, in a specific display format; and (c) transmitting, by the server, the display information generated in step (b) to the display device.

Abstract: An information sharing method that provides a graphical user interface image for sharing information relating to an appliance within a home among a plurality of users includes a receiving step of receiving, as home appliance event information, information on a state change of an appliance within a plurality of homes, a priority determining step of determining a priority of a home that is to be displayed in the graphical user interface image in accordance with an occurrence frequency of the home appliance event information within each home, and a home determining step of determining a home to be displayed in the graphical user interface image in accordance with the priority.

Abstract: An image compression device which compresses image data, including: a first quantization unit which performs a quantization mode 1 to quantize pixel values using two values A1 and B1 (A1<B1), in one range defined by A1 and B1; a second quantization unit which performs a quantization mode 2 to quantize the pixel values using two values A2 and B2 (A2>B2), in two ranges defined by A2 and B2; and a compressed data generation unit which generates compressed data including a value A, a value B, and quantized values of the pixel values quantized in a selected quantization mode, wherein the compressed data generation unit generates the compressed data using: A1 and B1 as A and B, respectively, when the quantization mode 1 is selected; and A2 and B2 as A and B, respectively, when the quantization mode 2 is selected.

Abstract: An image compression device which compresses image data, including: a first quantization unit which performs a quantization mode 1 to quantize pixel values using two values A1 and B1 (A1<B1), in one range defined by A1 and B1; a second quantization unit which performs a quantization mode 2 to quantize the pixel values using two values A2 and B2 (A2>B2), in two ranges defined by A2 and B2; and a compressed data generation unit which generates compressed data including a value A, a value B, and quantized values of the pixel values quantized in a selected quantization mode, wherein the compressed data generation unit generates the compressed data using: A1 and B1 as A and B, respectively, when the quantization mode 1 is selected; and A2 and B2 as A and B, respectively, when the quantization mode 2 is selected.