Saved in:
Bibliographic Details
Main Authors: Xu, Bin, Banerjee, Ayan, Gupta, Sandeep K. S.
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.02283
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909939893534720
author Xu, Bin
Banerjee, Ayan
Gupta, Sandeep K. S.
author_facet Xu, Bin
Banerjee, Ayan
Gupta, Sandeep K. S.
contents Model Recovery (MR) enables safe, explainable decision making in mission-critical autonomous systems (MCAS) by learning governing dynamical equations, but its deployment on edge devices is hindered by the iterative nature of neural ordinary differential equations (NODEs), which are inefficient on FPGAs. Memory and energy consumption are the main concerns when applying MR on edge devices for real-time operation. We propose MERINDA, a novel FPGA-accelerated MR framework that replaces iterative solvers with a parallelizable neural architecture equivalent to NODEs. MERINDA achieves nearly 11x lower DRAM usage and 2.2x faster runtime compared to mobile GPUs. Experiments reveal an inverse relationship between memory and energy at fixed accuracy, highlighting MERINDA's suitability for resource-constrained, real-time MCAS.
format Preprint
id arxiv_https___arxiv_org_abs_2512_02283
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Model Recovery at the Edge under Resource Constraints for Physical AI
Xu, Bin
Banerjee, Ayan
Gupta, Sandeep K. S.
Artificial Intelligence
Model Recovery (MR) enables safe, explainable decision making in mission-critical autonomous systems (MCAS) by learning governing dynamical equations, but its deployment on edge devices is hindered by the iterative nature of neural ordinary differential equations (NODEs), which are inefficient on FPGAs. Memory and energy consumption are the main concerns when applying MR on edge devices for real-time operation. We propose MERINDA, a novel FPGA-accelerated MR framework that replaces iterative solvers with a parallelizable neural architecture equivalent to NODEs. MERINDA achieves nearly 11x lower DRAM usage and 2.2x faster runtime compared to mobile GPUs. Experiments reveal an inverse relationship between memory and energy at fixed accuracy, highlighting MERINDA's suitability for resource-constrained, real-time MCAS.
title Model Recovery at the Edge under Resource Constraints for Physical AI
topic Artificial Intelligence
url https://arxiv.org/abs/2512.02283