Abstract: A data generation unit 6 generates a first number of false data based on a generation model that is a neural network for generating false data. A discriminator unit 7 derives output values for given data based on a discriminator model that is a neural network for deriving output values indicating true data-likeness and false data-likeness of the given data. A gradient information calculation unit 8 calculates, for each combination of one true data and each of the first number of false data, a distance between the output value for the true data and the output value for the false data, and calculates gradient information that is an update amount for each weight that the discriminator model has, so as to increase the distance by a predetermined amount. A selection unit 9 selects false data to be stored in the saved data storage unit 4.

Abstract: An information processing system includes: an input unit that inputs a feature quantity; a transform unit that performs a discrete wavelet transform on the feature quantity; a decomposition unit that decomposes a result of the discrete wavelet transform into a first frequency component and a second frequency component; a first processing unit that performs a convolution process on the first frequency component; a second processing unit that performs a convolution process on the second frequency component; an integration unit that integrates a result of the convolution process for the first frequency component and a result of the convolution process for the second frequency component, thereby to generate an integrated information; and an output unit that outputs the integrated information.

Abstract: An ink refill container includes a container main body including an ink storage chamber, an ink outlet-forming portion provided on an end portion of the container main body forming an ink outlet that allows the ink to flow out from the ink storage chamber, and a valve provided in the ink outlet-forming portion configured to openably seal the ink outlet, in which the ink outlet-forming portion includes a positioning portion on an outer side of the ink outlet-forming portion. in which the positioning portion is closer to the container main body than the valve is to the container main body in a central axis direction of the ink outlet, and in which the positioning portion partially abuts against an ink tank when the valve is opened for refilling the ink to the ink tank, to thereby position the valve relative to the ink tank.

Abstract: To generate and present effective information for making and determining a product design, this product design generation support device includes: an acquisition unit; a design classification unit; and an output unit. The acquisition unit acquires design information of each of a plurality of designs of the subject product that are different to each other and line-of-sight information of the subject person for those designs. The design classification unit classifies the plurality of designs into a plurality of groups according to the acquired design information and line-of-sight information. The output unit outputs the classification results.

Abstract: The acquisition unit acquires a design image relating to the design of the target product. The estimation unit uses the design image and an estimation model and estimates opinion information and line-of-sight information of a target person regarding the design of the target product. The estimation model is a model obtained by switching persons and products in various ways to learn the relation between, on the one hand, training product information, including product design images, and training attribute information about persons, and, on the other hand, training line-of-sight information of the persons regarding the product designs and training opinion information of the persons regarding the product designs. The output unit outputs the line-of-sight information and the opinion information estimated by the estimation unit.

Abstract: In order to generate and present information that is effective for preparing and determining a product design, a product-design generation support device according to the present invention is provided with an acquisition unit, a classification unit, and an output unit. The acquisition unit acquires design information representing a target design for a target product, as well as gaze information of a plurality of target persons in relation to the target design. The classification unit classifies the plurality of target persons into a plurality of groups on the basis of the acquired design information and gaze information. The output unit outputs the result of the classification.

Abstract: A purchasing factor estimation device includes: an acquisition unit that acquires person attribute information relating to a first person and product attribute information relating to a first product; an estimation unit that, on the basis of the person attribute information and the product attribute information, uses an estimation model to estimate the first person's degree of interest in the first product; and an output unit that outputs the first person's estimated degree of interest and an estimation reason therefor. The factors behind the purchase of a product by a customer are determined as a result of generating the estimation model by learning the relationship among person attribute information relating to a second person, product attribute information relating to a second product, line of sight information of the second person in relation to the second product, and the second person's degree of interest in the second product.

Abstract: A method for operating a hyper network machine learning system, the method including training a hyper network configured to generate main network parameters for a main network and generating, using the trained hyper network, the main network with the main network parameters, the main network having a machine learning architecture that models a spatial domain and a frequency domain to simulate a physical system.

Abstract: The present invention provides an information provision system (10) including: a determination unit (11) that determines an object of interest to a customer present in a facility among displayed articles present in the facility, based on attribute information of the customer; an estimation unit (12) that estimates the displayed article visually recognized by the customer, based on a content of behavior of the customer in the facility; a decision unit (13) that decides the displayed article of which information is provided to the customer, based on a result of the determination and a result of the estimation; and an output unit (14) that outputs information of the displayed article decided as an object of information provision.

Abstract: A data processing apparatus (2) includes: a calculation unit (24) for calculating a map information (AP) that represents a distribution of a vector component having a relatively high importance of a plurality of feature vector components that are included in a fourth feature vector (z4) obtained by synthesizing a first feature vector (z1) and a second feature vector (z2); and a generation unit (23) for generating a third feature vector (z3) by using the fourth feature vector (z4) and the map information.

Abstract: A gaze estimation system includes: a display control unit that allows a point to look at where a target person looks at to be displayed to move in a predetermined moving aspect; a detection unit that detects a movement of eyes of the target person from an image of the target person; and a tracking determination unit that determines whether or not the eyes of the target person are following the point to look at on the basis of a relationship between the eye movement and a movement of the point to look at. According to such a gaze estimation system, the eye movement of the target person can be detected more appropriately.

Abstract: A data generation apparatus (2) has: an obtaining unit (21) that obtains real data (D_real); a fake data generating unit (22) that generates fake data (D_fake) that imitates the real data; and a mix data generating unit (23) that generates mix data (D_mix) by mixing the real data and the fake data at a desired mix ratio (a), the mix data generating unit changes the mix ratio that is used to generate a data element of the mix data based on a position of the data element in the mix data.

Abstract: A learning system includes teacher DNN feature extraction unit extracting a feature of each of a plurality of training data, teacher DNN estimate calculation unit calculating a first estimate of a label corresponding to each of the training data, student DNN feature extraction unit extracting a feature of each of the training data, student DNN estimate calculation unit calculating a second estimate of a label corresponding to each of the training data, noisy label correction unit determining whether or not the label corresponding to the training data is a label including a noise, based on the label corresponding to the training data and the first estimate, and update unit updating weights in the student DNN so as to reduce a difference between the feature extracted by the teacher DNN feature extraction unit and the feature extracted by the student DNN feature extraction unit while decreasing an influence of the label including the noise.

Abstract: A gaze point detection device 30 includes face detection means 31 for detecting a face portion of an object person from a first image and first depth information, line of sight direction estimation means 32 for estimating a line of sight direction of the object person using the face portion detected by the face detecting means 31, position information estimation means 33 for estimating a three-dimensional spatial position of a pupil of the object person and three-dimensional spatial positions of a first photographing unit and a second photographing unit, based on the first image, the first depth information, a second image and second depth information, and gaze point identification means 34 for identifying a gaze point of the object person, based on the three-dimensional spatial position of the pupil of the object person and the line of sight direction.