In one example implementation according to aspects of the present disclosure, a computer-implemented method includes capturing a plurality of images at a camera associated with a vehicle and storing image data associated with the plurality of images to a memory. The method further includes dispatching vehicle perception tasks to a plurality of processing elements of an accelerator in communication with the memory. The method further includes performing, by at least one of the plurality of processing elements, the vehicle perception tasks for the vehicle perception using a neural network, wherein performing the vehicle perception tasks comprises performing an activation bypass for values below a first threshold, and performing weight pruning of synapses and neurons of the neural network based at least in part on a second threshold. The method further includes controlling the vehicle based at least in part on a result of performing the vehicle perception tasks.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Activation zero-bypass and weight pruning in neural networks for vehicle perception systems


    Beteiligte:
    ZENG SHUQING (Autor:in) / TONG WEI (Autor:in) / WANG SHIGE (Autor:in) / MILLETT ROMAN L (Autor:in)

    Erscheinungsdatum :

    22.03.2022


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Englisch


    Klassifikation :

    IPC:    G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / 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



    ACTIVATION ZERO-BYPASS AND WEIGHT PRUNING IN NEURAL NETWORKS FOR VEHICLE PERCEPTION SYSTEMS

    ZENG SHUQING / TONG WEI / WANG SHIGE et al. | Europäisches Patentamt | 2020

    Freier Zugriff

    Techniques for pruning neural networks

    DILIP SEQUEIRA / PAVLO MOLCHANOV / GREGORY HEINRICH et al. | Europäisches Patentamt | 2022

    Freier Zugriff

    TECHNIQUES FOR PRUNING NEURAL NETWORKS

    SEQUEIRA DILIP / MOLCHANOV PAVLO / HEINRICH GREGORY et al. | Europäisches Patentamt | 2022

    Freier Zugriff

    Pruning unmanned aerial vehicle

    LI LINRUI / ZHANG LIBO / ZHANG TAO et al. | Europäisches Patentamt | 2025

    Freier Zugriff

    Pruning CNNs for LiDAR-based Perception in Resource Constrained Environments

    Vemparala, Manoj Rohit / Singh, Anmol / Mzid, Ahmed et al. | IEEE | 2021