Quantized neural networks (QNNs) are increasingly considered for adoption on multiple applications, thanks to their high accuracy, but also since they allow for significantly lower compute and memory footprints. While the theory behind QNNs is achieving a high level of maturity, several new challenges have arisen during QNN deployment. Reliable and safe implementations of QNN accelerators becomes pivotal, especially when targeting safety critical applications like automotive, industrial and aerospace, requiring innovative solutions and their careful evaluation. In this work we compare the accuracy of QNNs during accelerated radiation testing when trained with different methodologies and implemented with a dataflow architecture in field programmable gate arrays (FPGA). The initial experiment shows that QNNs trained with a novel methodology, called fault-aware training (FAT), which accounts for soft errors during neural network (NN) training, makes QNNs more resilient to single-event-effects (SEEs) in FPGA.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Accelerated Radiation Test on Quantized Neural Networks trained with Fault Aware Training


    Beteiligte:


    Erscheinungsdatum :

    2022-03-05


    Format / Umfang :

    1576611 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Neural networks robot controller trained with evolution strategies

    Berlanga de Jesús, Antonio / Isasi, Pedro / Sanchis de Miguel, María Araceli et al. | BASE | 1999

    Freier Zugriff

    Channel-Aware Tracking in Multi-Hop Wireless Sensor Networks with Quantized Measurements

    Xiaojun Yang, / Ruixin Niu, / Masazade, Engin et al. | IEEE | 2013




    Neural networks trained with WiFi traces to predict airport passenger behavior

    Orsini, Federico / Gastaldi, Massimiliano / Mantecchini, Luca et al. | IEEE | 2019