A distribution of a plurality of predictions generated by a deep neural network using sensor data is calculated, and the deep neural network includes a plurality of neurons. At least one of a measurement or a classification corresponding to an object is determined based on the distribution. The deep neural network generates each prediction of the plurality of predictions with a different number of neurons.


    Access

    Download


    Export, share and cite



    Title :

    Measuring confidence in deep neural networks


    Contributors:

    Publication date :

    2023-05-23


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    English


    Classification :

    IPC:    G05D SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES , Systeme zum Steuern oder Regeln nichtelektrischer veränderlicher Größen / B60R Fahrzeuge, Fahrzeugausstattung oder Fahrzeugteile, soweit nicht anderweitig vorgesehen , VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR / G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / G06V



    MEASURING CONFIDENCE IN DEEP NEURAL NETWORKS

    SINGH GURJEET | European Patent Office | 2022

    Free access

    MEASURING CONFIDENCE IN DEEP NEURAL NETWORKS

    SINGH GURJEET | European Patent Office | 2021

    Free access

    Online Black-Box Confidence Estimation of Deep Neural Networks

    Woitschek, Fabian / Schneider, Georg | IEEE | 2022


    Confidence generation using neural networks

    NIKOLIC ZORAN / KISSAKANIN BORIS / VISITO ERIC et al. | European Patent Office | 2022

    Free access

    Deep Confidence Propagation Stereo Network

    Zeng, Kai / Wang, Yaonan / Wang, Wei et al. | IEEE | 2023