Abstract: A linguistic feature amount output part receives a text describing a base class image and outputs a linguistic feature amount. An image feature amount output part receives the base class image and outputs an image feature amount. A base class image selection part receives the linguistic feature amount, the image feature amount, and the base class image and selects a base class image corresponding to the image feature amount having a distance equal to or smaller than a predetermined threshold value from the linguistic feature amount. A neural network lower layer part receives the base class image selected by the base class image selection part and a novel class image and outputs a value based the base class image and a value based on the novel class image. A base class classification output part outputs a base class classification based on the base class image and the novel class image. A novel class classification output part outputs a novel class classification based on the novel class image.

Abstract: A novel class image generation part processes a base class image to generate a novel class image. An image feature amount output part is pre-trained on the base class images, receives the base class image or the novel class image, and outputs an image feature amount. A linguistic classification weight output part is pre-trained on the base class images and sentences describing the base class images, receives a sentence describing the base class image, and outputs a linguistic classification weight. An image classification weight output part receives the image feature amount, calculates an average value of the image feature amount for each class, and outputs the average value as an image classification weight for each class. An optimization part receives the image classification weight and the linguistic classification weight, optimizes the image classification weight, and outputs a reconstructed classification weight.

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: 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 machine learning apparatus that continually learns a novel class with fewer samples than a base class is provided. A base class feature extraction unit extracts a feature vector of the base class. A novel class feature extraction unit extracts a feature vector of the novel class. A merged feature calculation unit merges the feature vector of the base class and the feature vector of the novel class to calculate a merged feature vector that merges the base class and the novel class. A learning unit classifies, on a projected space, a query sample of a query set based on a distance between a position of the merged feature vector of the query sample of the query set and a position of a classification weight vector of each class, and learns a classification weight vector of the novel class to minimize a loss incurred in classification.

Abstract: A pre-trained feature extraction unit extracts feature vectors of samples in a base class using a pre-trained model. A base class classification weight is for classifying the samples in the base class using the classification weight of the base class while using the feature vectors of the samples in the base class as input. A feature optimization unit performs meta-learning of an optimization module that is based on the pre-trained model and optimizes feature vectors of samples in a novel class. A novel class feature averaging unit averages the feature vectors of the samples in the novel class for each class and calculates the classification weight of the novel class. A graph neural network uses the classification weights of the base class and novel class as input, performs meta-learning of the dependence relationship between the base and novel classes, and outputs a reconstruction classification weight.

Abstract: A feature extraction unit extracts a feature vector from input data. A semantic prediction unit is a module has been trained in advance in a meta-learning process and that generates a semantic vector from the feature vector of the input data. A mapping unit is a module that has learned a base class and that generates a semantic vector from the feature vector of the input data. An optimization unit optimizes parameters of the mapping unit using the semantic vector generated by the semantic prediction unit as a correct answer semantic vector such that a distance between the semantic vector generated by the mapping unit and the correct answer semantic vector is minimized when semantic information is not added to input data of a novel class at the time of learning the novel class.

Abstract: A machine learning device is provided that performs continual learning of a fewer number of novel classes than the number of base classes. A base class feature extraction unit extracts feature vectors of the base classes. A novel class feature extraction unit extracts feature vectors of the novel classes. A mixture feature calculation unit mixes the feature vectors of the base classes and the feature vectors of the novel classes and calculates a mixture feature vector of the base classes and the novel classes. A learning unit classifies a query sample of a query set based on the distance between the position of a mixture feature vector of the query sample of the query set and the position of a classification weight vector of each class in a projection space and learns classification weight vectors of the novel classes so as to minimize classification loss.

Abstract: A basic class selection unit selects, in response to input data, a base class based on an embedding vector output by a basic neural network that has learned the base class and a centroid vector of the base class. A continual learning unit continually learns an additional class by using an additional neural network that has learned the base class. An additional class selection unit selects, in response to the input data, an additional class based on an embedding vector output by the additional neural network subjected to continual learning and centroid vectors of the base class and the additional class. A classification determination unit classifies the input data based on the base class selected by the base class selection unit and the additional class selected by the additional class selection unit.

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 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: 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 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: 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.