Abstract: Neural network classification may be performed by inputting a training data set into each of a plurality of first neural networks, the training data set including a plurality of samples, obtaining a plurality of output value sets from the plurality of first neural networks, each output value set including a plurality of output values corresponding to one of the plurality of samples, each output value being output from a corresponding first neural network in response to the inputting of one of the samples of the training data set, inputting the plurality of output value sets into a second neural network, and training the second neural network to output an expected result corresponding to each sample in response to the inputting of a corresponding output value set.

Abstract: Methods and systems are provided for training a neural network with augmented data. A dataset comprising a plurality of classes is obtained for training a neural network. Prior to initiation of training, the dataset may be augmented by performing affine transformations of the data in the dataset, wherein the amount of augmentation is determined by a data augmentation variable. The neural network is trained with the augmented dataset. A training loss and a difference of class accuracy for each class is determined. The data augmentation variable is updated based on the total loss and class accuracy for each class. The dataset is augmented by performing affine transformations of the data in the dataset according to the updated data augmentation variable, and the neural network is trained with the augmented dataset.

Abstract: A computer implemented method trains an image recognition model. A set of processor units creates a saliency map of an original image. The set of processor units superimposes the saliency map on the original image to form an augmented image, wherein the augmented image is used to train the image recognition model.

Abstract: Image classification using a generated mask image is performed by generating a mask image that extracts a target area from an input image, extracting an image feature map of the input image by inputting the input image in a first neural network including at least one image feature extracting layer, masking the image feature map by using the mask image, and classifying the input image by inputting the masked image feature map to a second neural network including at least one classification layer.

Abstract: A determination is made of an explanatory variable with respect to an objective variable. A subset of data from data to be analyzed is created, in response to setting the objective variable to be analyzed to perform analysis. Association analysis is applied to analysis results, in response to a number of analysis runs exceeding a predetermined number. An association rule is derived for the explanatory variable from a result of the association analysis. An explanatory variable having a relevance value greater than a threshold value with the objective variable in the data to be analyzed is selected. The selected explanatory variable is scored as an input using the association rule to determine whether the explanatory variable is to be added or removed.

Abstract: A determination is made of an explanatory variable with respect to an objective variable. A subset of data from data to be analyzed is created, in response to setting the objective variable to be analyzed to perform analysis. Association analysis is applied to analysis results, in response to a number of analysis runs exceeding a predetermined number. An association rule is derived for the explanatory variable from a result of the association analysis. An explanatory variable having a relevance value greater than a threshold value with the objective variable in the data to be analyzed is selected. The selected explanatory variable is scored as an input using the association rule to determine whether the explanatory variable is to be added or removed.

Abstract: In an approach to improving accuracy through weak model aggregation, one or more computer processors generating a plurality of hyperparameter sets, wherein each hyperparameter set in the plurality of hyperparameter sets contains one or more hyperparameters varied to increase over-training in one or more models, wherein over-training includes overfitting or underfitting. The one or more computer processors create a plurality of weak models utilizing a created bootstrap dataset in a plurality of created bootstrap datasets, a corresponding extracted explanatory variable set, and a corresponding hyperparameter set in the generated plurality of hyperparameter sets, wherein each weak model in a created plurality of weak models shares at least the created bootstrap dataset, the extracted explanatory variable set, the generated hyperparameter set, a machine learning technique, or a model architecture.

Abstract: Neural network classification may be performed by inputting a training data set into each of a plurality of first neural networks, the training data set including a plurality of samples, obtaining a plurality of output value sets from the plurality of first neural networks, each output value set including a plurality of output values corresponding to one of the plurality of samples, each output value being output from a corresponding first neural network in response to the inputting of one of the samples of the training data set, inputting the plurality of output value sets into a second neural network, and training the second neural network to output an expected result corresponding to each sample in response to the inputting of a corresponding output value set.

Abstract: Neural network classification may be performed by inputting a training data set into each of a plurality of first neural networks, the training data set including a plurality of samples, obtaining a plurality of output value sets from the plurality of first neural networks, each output value set including a plurality of output values corresponding to one of the plurality of samples, each output value being output from a corresponding first neural network in response to the inputting of one of the samples of the training data set, inputting the plurality of output value sets into a second neural network, and training the second neural network to output an expected result corresponding to each sample in response to the inputting of a corresponding output value set.

Abstract: In an approach to improving accuracy through weak model aggregation, one or more computer processors generating a plurality of hyperparameter sets, wherein each hyperparameter set in the plurality of hyperparameter sets contains one or more hyperparameters varied to increase over-training in one or more models, wherein over-training includes overfitting or underfitting. The one or more computer processors create a plurality of weak models utilizing a created bootstrap dataset in a plurality of created bootstrap datasets, a corresponding extracted explanatory variable set, and a corresponding hyperparameter set in the generated plurality of hyperparameter sets, wherein each weak model in a created plurality of weak models shares at least the created bootstrap dataset, the extracted explanatory variable set, the generated hyperparameter set, a machine learning technique, or a model architecture.

Abstract: There is a desire to accurately learn a detection model. Provided is a computer-implemented method including acquiring an input image; acquiring an annotated image designating a region of interest in the input image; inputting the input image to a detection model that generates an output image showing a target region from the input image; calculating an error between the output image and the annotated image, using a loss function that weights an error inside the region of interest more heavily than an error outside the region of interest; and updating the detection model in a manner to reduce the error.

Abstract: There is a desire to accurately learn a detection model. Provided is a computer-implemented method including acquiring an input image; acquiring an annotated image designating a region of interest in the input image; inputting the input image to a detection model that generates an output image showing a target region from the input image; calculating an error between the output image and the annotated image, using a loss function that weights an error inside the region of interest more heavily than an error outside the region of interest; and updating the detection model in a manner to reduce the error.