The invention relates to a method for training a machine learning system (1) to quantify uncertainties (U) in output data (Y'). In this method, training data (X, Y), comprising training input data (X) and training target values (Y), are provided. These training data (X, Y) are used to adjust parameters of the machine learning system (1) such that the machine learning system (1), when the training input data (X) are input, generates output data (Y') similar to the training target values (Y); and generates reconstruction data (X'; Y'') that represent a measure of the familiarity of training data (X, Y). The invention furthermore relates to a method for quantifying uncertainties (U) in output data (Y') of a machine learning system (1) that has been trained in accordance with the method described above. In this method, the machine learning system (1) generates output data (Y') from input data (X) and the machine learning system (1) generates reconstruction data (X'; Y''). A metric (4), the reconstruction data (X'; Y'') and data (X; Y') corresponding to the reconstruction data (X'; Y'') are used to generate a deviation value, wherein the deviation value is a measure of the familiarity of training data (X, Y) for the input data (X), quantifies the uncertainty (U) in the output data (Y') and is assigned to the output data (Y').


    Access

    Download


    Export, share and cite



    Title :

    VERFAHREN UND SYSTEM ZUR QUANTIFIZIERUNG VON UNSICHERHEITEN VON AUSGABEDATEN EINES MASCHINELLEN LERNSYSTEMS SOWIE VERFAHREN ZUM TRAINIEREN EINES MASCHINELLEN LERNSYSTEMS


    Additional title:

    METHOD AND SYSTEM FOR QUANTIFYING UNCERTAINTIES IN OUTPUT DATA FROM A MACHINE LEARNING SYSTEM AND METHOD FOR TRAINING A MACHINE LEARNING SYSTEM
    PROCÉDÉ ET SYSTÈME DE QUANTIFICATION D'INCERTITUDES DANS DES DONNÉES DE SORTIE D'UN SYSTÈME D'APPRENTISSAGE MACHINE ET PROCÉDÉ D'APPRENTISSAGE D'UN SYSTÈME D'APPRENTISSAGE MACHINE


    Contributors:

    Publication date :

    2024-10-09


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    German


    Classification :

    IPC:    G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / B60W CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION , Gemeinsame Steuerung oder Regelung von Fahrzeug-Unteraggregaten verschiedenen Typs oder verschiedener Funktion