Abstract: In an approach, a processor receives, at an edge device running a local instance of a machine learning (ML) model, a set of inference data comprising a plurality of datapoints, wherein the local instance of the ML model is a deployed version of the ML model running in a cloud environment, and wherein the ML model was trained in the cloud environment and then deployed to the edge device. A processor runs the plurality of datapoints through one or more filters to determine a probability for each datapoint of whether a respective datapoint should be sent back to the cloud environment and used for retraining the ML model. A processor determines, for each datapoint, whether the probability for the respective datapoint meets a send back threshold that is required to be met before the respective datapoint is sent back to the cloud environment.

Abstract: A sensor for provides a measurement and information about the validity of the measurement. The sensor includes a transducer for generating a data signal related to the value of a variable and a transmitter for receiving the data signal and generating output signals. The transmitter generates a first output signal related to the value of the variable. The transmitter also generates a second output signal based on a dynamic uncertainty analysis of the first output signal.