Abstract: An initialization rate determination unit determines, in accordance with a depth of a layer in a neural network model, a first initialization rate for initializing weights in the neural network model on a first task. A machine learning execution unit generates a neural network model trained on a first task by training on the first task by machine learning. An initialization unit initializes weights in the neural network model trained on the first task, based on the first initialization rate, to generate an initialized neural network model trained on the first task, the initialized neural network trained on the first task being used in a second task.

Abstract: A domain adaptation data richness determination unit determines, when a first model trained by using training data of a first domain is trained by transfer learning by using training data of a second domain, a domain adaptation data richness based on the number of items of training data of the second domain, the first model being a neural network. A learning layer determining unit determines a layer in the second model, which is a duplicate of the first model, targeted for training, based on the domain adaptation data richness. A transfer learning unit applies transfer learning to the layer in the second model targeted for training, by using the training data of the second domain.

Abstract: A weight storage unit stores weights of a plurality of filters used to detect a feature of a task. A continual learning unit trains the weights of the plurality of filters in response to an input task in continual learning. A filter control unit compares, after a predetermined epoch number has been learned in continual learning, the weight of a filter that has learned the task with the weight of a filter that is learning the task, extracts overlap filters having a similarity in weight equal to or greater than a predetermined threshold value as shared filters shared by tasks, and leaves one of the overlap filters as the shared filter and initializes the weights of filters other than the shared filter.

Abstract: A weight storage unit stores weights of a plurality of filters used to detect a feature of a task. A continual learning unit trains the weights of the filters in response to an input task in continual learning. A filter processing unit locks, of a plurality of filters that have learned one task, the weights of a proportion of the filters to prevent the proportion of the filters from being used to learn a further task and initializes the weights of other filters to use the other filters to learn a further task. A comparison unit compares the weights of a plurality of filters that have learned two or more tasks, extracts overlap filters having a similarity in weight over a threshold value as shared filters shared by tasks, leaves one of the overlap filters as the shared filter, and initializes the weights of filters other than the shared filter.

Abstract: An object recognition unit recognizes an object in an input image by using an object recognition model. A recognition precision determination unit determines a precision of recognition of the object in the input image. A supervised image conversion unit converts the input image for which the precision of recognition of the object is lower than a predetermined threshold value into a supervised image by labeling the input image based on a feature amount of the input image. A transfer learning unit applies transfer learning to the object recognition model by using the supervised image as training data to update the object recognition model.

Abstract: A domain adaptability determination unit determines a domain adaptability based on a precision of inference from images of a second domain using a first model trained by using images of a first domain as training data, the first model being a neural network. A learning layer determining unit determines a layer in the second model, which is a duplicate of the first model, targeted for training, based on the domain adaptability. A transfer learning execution unit applied transfer learning to the layer in the second model targeted for training, by using images of the second domain as training data.

Abstract: A visible light image generation model learning unit generates a trained visible light image generation model that generates a visible light image in a second time zone from a far-infrared image in a first time zone. The visible light image generation model learning unit includes a first learning unit that machine-learns the far-infrared image in the first time zone and a far-infrared image in the second time zone as teacher data and generates a trained first generation model that generates the far-infrared image in the second time zone from the far-infrared image in the first time zone, and a second learning unit that machine-learns the far-infrared image in the second time zone and the visible light image in the second time zone as teacher data and generates a trained second generation model that generates the visible light image in the second time zone from the far-infrared image in the second time zone.

Abstract: A far-infrared image acquisition unit acquires a far-infrared image. An image conversion unit converts the acquired far-infrared image into a visible light image. A visible light image trained model storage unit stores a first visible light image trained model having performed learning using the visible light image as training data. A transfer learning unit performs transfer learning on a first visible light image trained model by using the visible light image obtained by conversion as training data to generate a second visible light image trained model.

Abstract: A far-infrared image training data acquisition unit acquires a far-infrared image in a first predetermined time zone. A visible light image training data acquisition unit acquires a visible light image in a second predetermined time zone. A visible light image generation model training unit machine-learns the far-infrared image in the first predetermined time zone and the visible light image in the second predetermined time zone as training data by a generative adversarial network, and generates a trained generation model, which generates the visible light image in the second predetermined time zone from the far-infrared image in the first predetermined time zone. Through machine learning by a generative adversarial network, the visible light image generation model training unit further generates a trained identification model, which identifies whether or not the far-infrared image is a far-infrared image captured in the first predetermined time zone.

Abstract: The game device includes a reception unit that is configured to receive instruction information created when a user performs an operation on an input device triggered by a sound output while a game progresses and a derivation unit that is configured to start measuring the degree of fatigue on the basis of the instruction information received by the reception unit and derive the degree of fatigue of the user on the basis of an operation performed by the user during the started measurement of the degree of fatigue.

Abstract: A map data analysis unit refers to map data for a game in which a plurality of players compete in a three-dimensional space to extract positional information on each player. A feature parameter extraction unit extracts a feature parameter related to the game. A spectating area analysis unit analyzes one or more areas in a map that should be viewed by spectators, based on the positional information on each player and the feature parameter related to the game. A map data generation unit generates spectating map data by associating information indicating the area that should be viewed by spectators with the map data.

Abstract: A game device includes a reception unit that is configured to receive operation information created when a user performs an operation on an input device while a game progresses, a determination unit that is configured to determine whether an operation of starting measurement of the degree of concentration has been performed on the basis of the operation information received by the reception unit, and a derivation unit that is configured to start measuring the degree of concentration if the determination unit determines that the operation of starting measurement of the degree of concentration has been performed and is configured to derive the degree of concentration of the user on the basis of an operation performed by the user during the started measurement of the degree of concentration.

Abstract: The game device includes a reception unit that is configured to receive instruction information created when a user performs an operation on an input device triggered by a sound output while a game progresses and a derivation unit that is configured to start measuring the degree of fatigue on the basis of the instruction information received by the reception unit and derive the degree of fatigue of the user on the basis of an operation performed by the user during the started measurement of the degree of fatigue.

Abstract: A map data analysis unit refers to map data for a game in which a plurality of players compete in a three-dimensional space to extract positional information on each player. A feature parameter extraction unit extracts a feature parameter related to the game. A spectating area analysis unit analyzes one or more areas in a map that should be viewed by spectators, based on the positional information on each player and the feature parameter related to the game. A map data generation unit generates spectating map data by associating information indicating the area that should be viewed by spectators with the map data.

Abstract: An imaging unit is configured to capture an image of a subject in the water. A lighting unit is configured to illuminate the subject. A histogram generator is configured to divide a range from the minimum to the maximum luminance values of a luminance signal, included in an image signal generated by capturing the image of the subject into a plurality of luminance groups, and to generate histogram data representing the distribution of frequencies of the plurality of luminance groups. Based on the generated histogram data, a histogram analyzer is configured to analyze the distribution of frequencies of the plurality of luminance groups. According to the result of the analysis for the histogram data by the histogram analyzer, a distance controller is configured to control to adjust the distance between the subject and the lighting unit.

Abstract: A multilayer circuit board includes a plurality of wiring layers laminated with insulation layers interposed therebetween, the multilayer circuit board further including a solder resist layer that covers a front face wiring layer formed on a front face side insulation layer, in which the front face wiring layer includes a pad for leg terminal to which a leg terminal of a connector is connected, the solder resist layer has an opening part for leg terminal which exposes a part of the pad for leg terminal, a via for leg terminal is provided beneath the pad for leg terminal in a predetermined range straddling a contour line of an opening part for leg terminal, and the via for leg terminal connects a first internal wiring layer with the pad for leg terminal.

Abstract: An imaging unit is configured to capture an image of a subject in the water. A lighting unit is configured to illuminate the subject. A histogram generator is configured to divide a range from the minimum to the maximum luminance values of a luminance signal, included in an image signal generated by capturing the image of the subject into a plurality of luminance groups, and to generate histogram data representing the distribution of frequencies of the plurality of luminance groups. Based on the generated histogram data, a histogram analyzer is configured to analyze the distribution of frequencies of the plurality of luminance groups. According to the result of the analysis for the histogram data by the histogram analyzer, a distance controller is configured to control to adjust the distance between the subject and the lighting unit.

Abstract: An RB rate calculator calculates an RB rate based on an R signal and a B signal. A starting point changing unit changes a starting point based on the RB rate. An offset calculating unit calculates an offset value to adjust for selection of a basic depth model type based on a bottom high frequency component evaluation value. An adding unit adds a signal from the starting point changing unit and an offset. Another adding unit adds an offset-added signal from the adding unit and a basic depth model-composed image signal supplied from a composing unit, and generates depth estimation data wherein a degree of superimposition of object information is changed according to a composition of a composed image of basic depth models selected to be composed.

Abstract: A depth estimation data generating device includes a difference data generator and negative and positive shift amount generators. The difference data generator calculates the difference between a non-stereo image and the average value data of the average brightness of the non-stereo image to generate the difference data. The negative shift amount generator generates a negative shift amount, wherein the difference data generated using the minimum value data of the minimum brightness of the non-stereo image has a minimum value of shift amount and the shift amount approaches zero from the minimum value as the difference data approaches zero. The positive shift amount generator generates a positive shift amount, wherein the difference data generated using the maximum value data of the maximum brightness of the non-stereo image has a maximum value of shift amount and the shift amount approaches zero from the maximum value as the difference data approaches zero.

Abstract: A high frequency component detector detects a high frequency component of an R signal. A high frequency component comparator outputs a flag indicating a threshold value division range having the highest threshold value including a value of a high frequency component in a specific period. A gain calculating unit calculates a ratio as a gain, the ratio set according to the threshold value division range indicated by the flag input. A multiplying unit multiplies the R signal and the gain to generate an object signal R? wherein a concavity and convexity difference with adjacent pixels in a small region of an image is suppressed compared to the R signal.