Efficient Deployment of Spiking Neural Networks on SpiNNaker2 for DVS Gesture Recognition Using Neuromorphic Intermediate Representation
Authors:
- 25 March 2025
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Abstract
Spiking Neural Networks (SNNs) are highly energy-efficient during inference, making them particularly suitable for deployment on neuromorphic hardware. Their ability to process event-driven inputs, such as data from dynamic vision sensors (DVS), further enhances their applicability to edge computing tasks. However, the resource constraints of edge hardware necessitate techniques like weight quantization, which reduce the memory footprint of SNNs while preserving accuracy. Despite its importance, existing quantization methods typically focus on synaptic weights quantization without taking account of other critical parameters, such as scaling neuron firing thresholds.To address this limitation, we present the first benchmark for the DVS gesture recognition task using SNNs optimized for the many-core neuromorphic chip SpiNNaker2. Our study evaluates two quantization pipelines for fixed-point computations. The first approach employs post training quantization (PTQ) with percentile-based threshold scaling, while the second uses quantization aware training (QAT) with adaptive threshold scaling. Both methods achieve accurate 8-bit on-chip inference, closely approximating 32-bit floating-point performance. Additionally, our baseline SNNs perform competitively against previously reported results without specialized techniques. These models are deployed on SpiNNaker2 using the neuromorphic intermediate representation (NIR). Ultimately, we achieve 94.13% classification accuracy on-chip, demonstrating the SpiNNaker2’s potential for efficient, low-energy neuromorphic computing.Keywords
All Related Versions
Funding Information
- Horizon Europe
This publication has 21 references indexed in Scilit:
- Neuromorphic intermediate representation: A unified instruction set for interoperable brain-inspired computingNature Communications, 2024
- Spike-based dynamic computing with asynchronous sensing-computing neuromorphic chipNature Communications, 2024
- Language Modeling on a SpiNNaker2 Neuromorphic Chip2024
- Navigating Local Minima in Quantized Spiking Neural Networks2022
- Integer-Only Zero-Shot Quantization for Efficient Speech Recognition2022
- Q-SpiNN: A Framework for Quantizing Spiking Neural Networks2021
- Temporal Binary Representation for Event-Based Action Recognition2021
- An Efficient Spiking Neural Network for Recognizing Gestures with a DVS Camera on the Loihi Neuromorphic Processor2020
- Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference2018
- A Low Power, Fully Event-Based Gesture Recognition System2017