Abstract: An information processing device 1 includes: a feature area detection unit 28 that acquires, by inputting a target image showing a fastening part that is an inspected target to a machine learning model, a feature area based on an estimated coordinate that includes a feature point relating to reference indication added to the fastening part and relates to a position of the feature point and a distribution of the estimated coordinate; an uncertainty evaluation unit 29 that determines whether the feature area satisfies a prescribed reference; and a fastening state determination unit 30 that determines a fastening state of the fastening part based on the estimated coordinate when the feature area satisfies the prescribed reference.

Abstract: Predictively robust models are trained by embedding a distribution of each temporal data set among a plurality of temporal data sets into a feature vector, predicting a future feature vector of a distribution of a future data set, based on the feature vector of each temporal data set among a plurality of temporal data sets, creating the future data set from the future feature vector, perturbing the future data set to produce a plurality of perturbed future data sets, and training a learning function using the future data set and each perturbed future data set to produce a model.

Abstract: An information processing apparatus includes: a Soft Category Estimator configured to receive a plurality of Data Inputs which includes positive data and negative data and to estimate a soft category using predetermined parameters of a position, size and margin width of a rectangular pattern for classifying the Data Input as the positive data and the negative data; an Estimation Evaluator configured to compare the estimated soft category label with the true Data labels for the Data Input and output a feedback on the predetermined parameters; and a Parameter Modifier configured to modify the predetermined parameters to reduce a total loss to learn an optimal margined rectangular pattern for classifying the positive data and the negative data.

Abstract: A method of training an image recognition model includes masking a first region of a first image with a first portion of a second image to define a mixed image, wherein the first image is different from the second image, and a location of the first region in the first image corresponds to a location of the first portion in the second image. The method further includes performing masked global average pooling (GAP) on both the mixed image. The method further includes generating a first classification score for the first image and a second classification score for the second image based on the masked GAP of the mixed image.

Abstract: Forward compatible models are obtained by operations including training a learning function with a current training data set to produce a first model, the current training data set including a plurality of samples, generating a plurality of prospective models, each prospective model based on a variation of one of the current training data set or the first model, adjusting a plurality of sample weights based on output of one or more prospective models among the plurality of prospective models in response to input of the current training data set, and retraining the learning function with the current training data set and the plurality of sample weights to produce a second model.

Abstract: Distributionally robust models are obtained by operations including training, according to a loss function, a first learning function with a training data set to produce a first model, the training data set including a plurality of samples. The operations may further include training a second learning function with the training data set to produce a second model, the second model having a higher accuracy than the first model. The operations may further include assigning an adversarial weight to each sample among the plurality of samples set based on a difference in loss between the first model and the second model. The operations may further include retraining, according to the loss function, the first learning function with the training data set to produce a distrtibutionally robust model, wherein during retraining the loss function further modifies loss associated with each sample among the plurality of samples based on the assigned adversarial weight.