Hardware-aware vs. Hardware-agnostic Energy Estimation for SNN in Space Applications

• URL: http://arxiv.org/abs/2508.19654v1
• Date: Wed, 27 Aug 2025 08:03:58 GMT
• Title: Hardware-aware vs. Hardware-agnostic Energy Estimation for SNN in Space Applications
• Authors: Matthias Höfflin, Jürgen Wassner,
• Abstract summary: Spiking Neural Networks (SNNs) have long been considered inherently energy-efficient, making them attractive for resource-constrained domains such as space applications.<n>This work investigates SNNs for multi-output regression, specifically 3-D satellite position estimation from monocular images, and compares hardware-aware and hardware-agnostic energy estimation methods.<n>Energy analysis shows that while hardware-agnostic methods predict a consistent 50-60% energy advantage for SNNs over CNNs, hardware-aware analysis reveals that significant energy savings are realized only on neuromorphic hardware and with high input sparsity.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Spiking Neural Networks (SNNs), inspired by biological intelligence, have long been considered inherently energy-efficient, making them attractive for resource-constrained domains such as space applications. However, recent comparative studies with conventional Artificial Neural Networks (ANNs) have begun to question this reputation, especially for digital implementations. This work investigates SNNs for multi-output regression, specifically 3-D satellite position estimation from monocular images, and compares hardware-aware and hardware-agnostic energy estimation methods. The proposed SNN, trained using the membrane potential of the Leaky Integrate-and-Fire (LIF) neuron in the final layer, achieves comparable Mean Squared Error (MSE) to a reference Convolutional Neural Network (CNN) on a photorealistic satellite dataset. Energy analysis shows that while hardware-agnostic methods predict a consistent 50-60% energy advantage for SNNs over CNNs, hardware-aware analysis reveals that significant energy savings are realized only on neuromorphic hardware and with high input sparsity. The influence of dark pixel ratio on energy consumption is quantified, emphasizing the impact of data characteristics and hardware assumptions. These findings highlight the need for transparent evaluation methods and explicit disclosure of underlying assumptions to ensure fair comparisons of neural network energy efficiency.

Related papers

• Efficient Eye-based Emotion Recognition via Neural Architecture Search of Time-to-First-Spike-Coded Spiking Neural Networks [52.617096567601344]
  Time-to-first-spike (TTFS)-coded spiking neural networks (SNNs) offer a promising solution for eye-based emotion recognition.<n>TTFS-ER is the first neural architecture search framework tailored to TTFS SNNs for eye-based emotion recognition.<n>When deployed on neuromorphic hardware, TNAS-ER attains a low latency of 48 ms and an energy consumption of 0.05 J.
  arXiv  Detail & Related papers  (2025-12-02T06:35:49Z)
• Energy efficiency analysis of Spiking Neural Networks for space applications [43.91307921405309]
  Spiking Neural Networks (SNN) are highly attractive due to their theoretically superior energy efficiency.<n>This work presents a numerical analysis and comparison of different SNN techniques applied to scene classification for the EuroSAT dataset.
  arXiv  Detail & Related papers  (2025-05-16T16:29:50Z)
• Differential Coding for Training-Free ANN-to-SNN Conversion [45.70141988713627]
  Spiking Neural Networks (SNNs) exhibit significant potential due to their low energy consumption.<n> converting Artificial Neural Networks (ANNs) to SNNs is an efficient way to achieve high-performance SNNs.<n>This article introduces differential coding for ANN-to-SNN conversion, a novel coding scheme that reduces spike counts and energy consumption.
  arXiv  Detail & Related papers  (2025-03-01T02:17:35Z)
• Reconsidering the energy efficiency of spiking neural networks [4.37952937111446]
  Spiking Neural Networks (SNNs) promise higher energy efficiency over conventional Quantized Artificial Neural Networks (QNNs)<n>This paper presents a rigorous re-evaluation of the true energy benefits of SNNs.
  arXiv  Detail & Related papers  (2024-08-29T07:00:35Z)
• Advancing Spiking Neural Networks for Sequential Modeling with Central Pattern Generators [47.371024581669516]
  Spiking neural networks (SNNs) represent a promising approach to developing artificial neural networks. Applying SNNs to sequential tasks, such as text classification and time-series forecasting, has been hindered by the challenge of creating an effective and hardware-friendly spike-form positional encoding strategy. We propose a novel PE technique for SNNs, termed CPG-PE. We demonstrate that the commonly used sinusoidal PE is mathematically a specific solution to the membrane potential dynamics of a particular CPG.
  arXiv  Detail & Related papers  (2024-05-23T09:39:12Z)
• Is Conventional SNN Really Efficient? A Perspective from Network Quantization [7.04833025737147]
  Spiking Neural Networks (SNNs) have been widely praised for their high energy efficiency and immense potential. However, comprehensive research that critically contrasts and correlates SNNs with quantized Artificial Neural Networks (ANNs) remains scant. This paper introduces a unified perspective, illustrating that the time steps in SNNs and quantized bit-widths of activation values present analogous representations.
  arXiv  Detail & Related papers  (2023-11-17T09:48:22Z)
• Are SNNs Truly Energy-efficient? $-$ A Hardware Perspective [7.539212567508529]
  Spiking Neural Networks (SNNs) have gained attention for their energy-efficient machine learning capabilities. This work studies two hardware benchmarking platforms for large-scale SNN inference, namely SATA and SpikeSim.
  arXiv  Detail & Related papers  (2023-09-06T22:23:22Z)
• A Hybrid Neural Coding Approach for Pattern Recognition with Spiking Neural Networks [53.31941519245432]
  Brain-inspired spiking neural networks (SNNs) have demonstrated promising capabilities in solving pattern recognition tasks. These SNNs are grounded on homogeneous neurons that utilize a uniform neural coding for information representation. In this study, we argue that SNN architectures should be holistically designed to incorporate heterogeneous coding schemes.
  arXiv  Detail & Related papers  (2023-05-26T02:52:12Z)
• Hybrid SNN-ANN: Energy-Efficient Classification and Object Detection for Event-Based Vision [64.71260357476602]
  Event-based vision sensors encode local pixel-wise brightness changes in streams of events rather than image frames. Recent progress in object recognition from event-based sensors has come from conversions of deep neural networks. We propose a hybrid architecture for end-to-end training of deep neural networks for event-based pattern recognition and object detection.
  arXiv  Detail & Related papers  (2021-12-06T23:45:58Z)
• Progressive Tandem Learning for Pattern Recognition with Deep Spiking Neural Networks [80.15411508088522]
  Spiking neural networks (SNNs) have shown advantages over traditional artificial neural networks (ANNs) for low latency and high computational efficiency. We propose a novel ANN-to-SNN conversion and layer-wise learning framework for rapid and efficient pattern recognition.
  arXiv  Detail & Related papers  (2020-07-02T15:38:44Z)
• SiamSNN: Siamese Spiking Neural Networks for Energy-Efficient Object Tracking [20.595208488431766]
  SiamSNN is the first deep SNN tracker that achieves short latency and low precision loss on the visual object tracking benchmarks OTB2013, VOT2016, and GOT-10k. SiamSNN notably achieves low energy consumption and real-time on Neuromorphic chip TrueNorth.
  arXiv  Detail & Related papers  (2020-03-17T08:49:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.