Abstract: An example computer-implemented image processing method includes receiving a digital image including a face area of a person and a background area, receiving an input parameter for modification of a feature of hair on the person, modifying the digital image based on the input parameter utilizing a generative neural network to create a modified digital image in which the feature of the hair on the person is modified, extracting a hair area from the modified digital image, and the face area and the background area from the digital image, and combining the face area and the background area from the digital image with the hair area from the modified digital image to create a composite modified digital image that includes data representing a modified feature of hair on the person from the modified digital image and data representing the face area and the background area from the digital image.

Abstract: An example computer-implemented image processing method includes receiving a digital image including a face area of a first subject and a background area, receiving a reference image of a second subject, modifying the digital image based on the reference image utilizing a generative neural network to create a modified digital image in which a feature of the second subject is transferred to the first subject, and combining the face area of the first subject and the background area from the digital image with the feature area from the modified digital image to create a composite modified digital image that includes data representing the feature of the second subject transferred to the first subject from the modified digital image and data representing the face area of the first subject and the background area from the digital image.

Abstract: This disclosure relates to learning with transformed data such as determining multiple training samples from multiple data samples. Each of the multiple data samples comprises one or more feature values and a label that classifies that data sample. A processor determines each of the multiple training samples by randomly selecting a subset of the multiple data samples, and combining the feature values of the data samples of the subset based on the label of each of the data samples of the subset. Since the training samples are combinations of randomly chosen data samples, the training samples can be provided to third parties without disclosing the actual training data. This is an advantage over existing methods in cases where the data is confidential and should therefore not be shared with a learner of a classifier, for example.

Abstract: This disclosure relates to learning from distributed data. In particular, it relates to determining multiple first training samples from multiple first data samples. Each of the multiple first data samples comprises multiple first feature values and a first label that classifies that first data sample. A processor determines each of the multiple first training samples by selecting a first subset of the multiple first data samples such that the first subset comprises data samples with corresponding one or more of the multiple first feature values, and combining the first feature values of the data samples of the first subset based on the first label of each of the first data samples of the first subset. The resulting training samples can be combined with training samples from other databases that share the same corresponding features and entity matching is unnecessary.

Abstract: A lossy data compressor for physical measurement data, comprising a parametrized mapping network hat, when applied to a measurement data point x in a space X, produces a point z in a lower-dimensional manifold Z, and configured to provide a point z on manifold Z as output in response to receiving a data point x as input, wherein the manifold Z is a continuous hypersurface that only admits fully continuous paths between any two points on the hypersurface; and the parameters ? of the mapping network are trainable or trained towards an objective that comprises minimizing, on the manifold Z, a distance between a given prior distribution PZ and a distribution PQ induced on manifold Z by mapping a given set PD of physical measurement data from X onto Z using the mapping network, according to a given distance measure.

Abstract: A lossy data compressor for physical measurement data, comprising a parametrized mapping network hat, when applied to a measurement data point x in a space X, produces a point z in a lower-dimensional manifold Z, and configured to provide a point z on manifold Z as output in response to receiving a data point x as input, wherein the manifold Z is a continuous hypersurface that only admits fully continuous paths between any two points on the hypersurface; and the parameters ? of the mapping network are trainable or trained towards an objective that comprises minimizing, on the manifold Z, a distance between a given prior distribution PZ and a distribution PQ induced on manifold Z by mapping a given set PD of physical measurement data from X onto Z using the mapping network, according to a given distance measure.

Abstract: This disclosure relates to learning from distributed data. In particular, it relates to determining multiple first training samples from multiple first data samples. Each of the multiple first data samples comprises multiple first feature values and a first label that classifies that first data sample. A processor determines each of the multiple first training samples by selecting a first subset of the multiple first data samples such that the first subset comprises data samples with corresponding one or more of the multiple first feature values, and combining the first feature values of the data samples of the first subset based on the first label of each of the first data samples of the first subset. The resulting training samples can be combined with training samples from other databases that share the same corresponding features and entity matching is unnecessary.

Abstract: This disclosure relates to learning with transformed data such as determining multiple training samples from multiple data samples. Each of the multiple data samples comprises one or more feature values and a label that classifies that data sample. A processor determines each of the multiple training samples by randomly selecting a subset of the multiple data samples, and combining the feature values of the data samples of the subset based on the label of each of the data samples of the subset. Since the training samples are combinations of randomly chosen data samples, the training samples can be provided to third parties without disclosing the actual training data. This is an advantage over existing methods in cases where the data is confidential and should therefore not be shared with a learner of a classifier, for example.