Robert Boschgmbh

Maja Rudolph

Max Welling

João D Semedo

Hugues Narcisse Tchouankem

Filipe Condessa

Chen Qiu

Maximilian Stark

Sindy Lowe

Aodong Li

A simple and highly effective zero-shot anomaly detection approach is disclosed. The approach is compatible with a variety of established anomaly detection methods. The approach relies on training an anomaly detector, such as a neural network, on a meta-set in combination with batch normalization.

Adaptively centered representation for zero-shot anomaly detection methods

A computer-implemented system and method relate to object discovery. The system and method include receiving a source image and generating input data by associating each pixel of the source image with predetermined phase values. An encoder encodes the input data to generate latent representation data in spherical coordinates. A decoder decodes the latent representation data to generate spherical reconstruction data of the source image. The spherical reconstruction data includes a radial component and a plurality of phase components. A reconstructed image is generated based at least on the radial component. The reconstructed image is a reconstruction of the source image.

System and method with spherical autoencoder for object discovery

A wireless system includes a controller that is configured to measure a first Reference Signal Received Power (RSRP1) from a first carrier at a first time, measure a second Reference Signal Received Power (RSRP2) from a second carrier at a second time, annotate the RSRP1 to the first carrier and the RSRP2 to the second carrier, in response to the first time and the second time being within a contemporaneous period, associate the RSRP1 and RSRP2 to the contemporaneous period, create an N-Dimension vector of RSRP1 and RSRP2 at the contemporaneous period, process the N-Dimension vector via a trainable function to obtain a predicted data rate, and in response to the predicted data rate falling below a normal operating range threshold, operate the system in a low bandwidth mode.

Predictive quality of service via channel aggregation

A computer-implemented method of anomaly detection associated with graphical data includes receiving as input one or more input data sets, wherein the input data sets includes one or more graphs, utilizing a plurality of graph neural networks (GNNs) to identify an aggregate loss including a first loss and second loss associated with the input data set, wherein the aggregate loss is associated with embedding's of the GNNs, and outputting a notification associated with an anomaly detection when the first and second loss exceeds an anomaly-detection threshold.

Growing community of inventors

Madison, WI, United States of America

Maja Rudolph