The present invention provides a system and method of side-stepping the need to retrain neural network model after initially trained using a simulator by comparing real-world data to data predicted by the simulator for the same inputs, and developing a mapping correlation that adjusts real world data toward the simulation data. Thus, the decision logic developed in the simulation-trained model is preserved and continues to operate in an altered reality. A threshold metric of similarity can be initially provided into the mapping algorithm, which automatically adjusts real world data to adjusted data corresponding to the simulation data for operating the neural network model when the metric of similarity between the real world data and the simulation data exceeds the threshold metric. Updated learning can continue as desired, working in the background as conditions are monitored.


    Access

    Download


    Export, share and cite



    Title :

    Continuous learning of simulation trained deep neural network model


    Contributors:

    Publication date :

    2022-04-26


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    English


    Classification :

    IPC:    G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / B63B Schiffe oder sonstige Wasserfahrzeuge , SHIPS OR OTHER WATERBORNE VESSELS / G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung




    CONTINUOUS LEARNING OF SIMULATION TRAINED DEEP NEURAL NETWORK MODEL FOR FLOATING PRODUCTION PLATFORMS, VESSELS AND OTHER FLOATING SYSTEMS

    O'SULLIVAN JAMES FRANCIS / SIDARTA DJONI EKA / LIM HO JOON | European Patent Office | 2021

    Free access


    Large Eddy Simulation of Airfoil Flows Using Adjoint-Trained Deep Learning Closure Models

    Hickling, Tom / Sirignano, Justin / MacArt, Jonathan F. | AIAA | 2024