Saved in:
Bibliographic Details
Main Authors: Nijsink, Wim, Forlin, Bruno Endres, Yousefzadeh, Amirreza, Ottavi, Marco
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.00030
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909006588542976
author Nijsink, Wim
Forlin, Bruno Endres
Yousefzadeh, Amirreza
Ottavi, Marco
author_facet Nijsink, Wim
Forlin, Bruno Endres
Yousefzadeh, Amirreza
Ottavi, Marco
contents Neuromorphic, or spiking, processors are increasingly being considered for use in harsh, radiation-prone environments such as space and avionics, where energy efficiency and graceful degradation are essential. In this study, we propose and experimentally validate a radiation-testing methodology specifically designed for neuromorphic processors that employ on-chip synaptic plasticity. We map the open-source ODIN SNN processor with Spike-Dependent Synaptic Plasticity (SDSP) onto the FPGA and expose it to a high-energy neutron beam while continuously monitoring MNIST classification accuracy and recording the synaptic state. From these measurements, we extract SEU cross-sections for ODIN's synaptic memory and develop a calibrated fault model to inform a complementary fault-injection campaign. By comparing inference-only and online-learning configurations, we demonstrate that enabling SDSP can significantly extend the time to application-level failure and enable partial recovery from accumulated bit flips, with modest hardware overhead.
format Preprint
id arxiv_https___arxiv_org_abs_2605_00030
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Shooting Neutrons at Neurons: Radiation Testing of a Spiking Neural Network on Flash-Based FPGAs
Nijsink, Wim
Forlin, Bruno Endres
Yousefzadeh, Amirreza
Ottavi, Marco
Hardware Architecture
Systems and Control
Neuromorphic, or spiking, processors are increasingly being considered for use in harsh, radiation-prone environments such as space and avionics, where energy efficiency and graceful degradation are essential. In this study, we propose and experimentally validate a radiation-testing methodology specifically designed for neuromorphic processors that employ on-chip synaptic plasticity. We map the open-source ODIN SNN processor with Spike-Dependent Synaptic Plasticity (SDSP) onto the FPGA and expose it to a high-energy neutron beam while continuously monitoring MNIST classification accuracy and recording the synaptic state. From these measurements, we extract SEU cross-sections for ODIN's synaptic memory and develop a calibrated fault model to inform a complementary fault-injection campaign. By comparing inference-only and online-learning configurations, we demonstrate that enabling SDSP can significantly extend the time to application-level failure and enable partial recovery from accumulated bit flips, with modest hardware overhead.
title Shooting Neutrons at Neurons: Radiation Testing of a Spiking Neural Network on Flash-Based FPGAs
topic Hardware Architecture
Systems and Control
url https://arxiv.org/abs/2605.00030