SPARQ: Spiking Early-Exit Neural Networks for Energy-Efficient Edge AI

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Patne, Parth, Taheri, Mahdi, Mahani, Ali, Jenihhin, Maksim, Mahani, Reza, Herglotz, Christian
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915864455938048
author Patne, Parth
Taheri, Mahdi
Mahani, Ali
Jenihhin, Maksim
Mahani, Reza
Herglotz, Christian
author_facet Patne, Parth
Taheri, Mahdi
Mahani, Ali
Jenihhin, Maksim
Mahani, Reza
Herglotz, Christian
contents Spiking neural networks (SNNs) offer inherent energy efficiency due to their event-driven computation model, making them promising for edge AI deployment. However, their practical adoption is limited by the computational overhead of deep architectures and the absence of input-adaptive control. This work presents SPARQ, a unified framework that integrates spiking computation, quantization-aware training, and reinforcement learning-guided early exits for efficient and adaptive inference. Evaluations across MLP, LeNet, and AlexNet architectures demonstrated that the proposed Quantised Dynamic SNNs (QDSNN) consistently outperform conventional SNNs and QSNNs, achieving up to 5.15% higher accuracy over QSNNs, over 330 times lower system energy compared to baseline SNNs, and over 90 percent fewer synaptic operations across different datasets. These results validate SPARQ as a hardware-friendly, energy-efficient solution for real-time AI at the edge.
format Preprint
id arxiv_https___arxiv_org_abs_2603_14380
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SPARQ: Spiking Early-Exit Neural Networks for Energy-Efficient Edge AI
Patne, Parth
Taheri, Mahdi
Mahani, Ali
Jenihhin, Maksim
Mahani, Reza
Herglotz, Christian
Machine Learning
Artificial Intelligence
Hardware Architecture
Spiking neural networks (SNNs) offer inherent energy efficiency due to their event-driven computation model, making them promising for edge AI deployment. However, their practical adoption is limited by the computational overhead of deep architectures and the absence of input-adaptive control. This work presents SPARQ, a unified framework that integrates spiking computation, quantization-aware training, and reinforcement learning-guided early exits for efficient and adaptive inference. Evaluations across MLP, LeNet, and AlexNet architectures demonstrated that the proposed Quantised Dynamic SNNs (QDSNN) consistently outperform conventional SNNs and QSNNs, achieving up to 5.15% higher accuracy over QSNNs, over 330 times lower system energy compared to baseline SNNs, and over 90 percent fewer synaptic operations across different datasets. These results validate SPARQ as a hardware-friendly, energy-efficient solution for real-time AI at the edge.
title SPARQ: Spiking Early-Exit Neural Networks for Energy-Efficient Edge AI
topic Machine Learning
Artificial Intelligence
Hardware Architecture
url https://arxiv.org/abs/2603.14380