# Q-SpiNN: A Framework for Quantizing Spiking Neural Networks

arXiv: https://arxiv.org/abs/2107.01807 · HTML: https://mlsanity.com/paper/2107.01807/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 28 references that are in the map.
- First posted on arXiv 5 Jul 2021.

## Builds on (most cited first, 16 of 16)

- [Quantizing deep convolutional networks for efficient inference: A whitepaper](https://mlsanity.com/paper/1806.08342/) (2018)
- [Deep Learning with Limited Numerical Precision](https://mlsanity.com/paper/1502.02551/) (2015)
- [Deep Learning in Spiking Neural Networks](https://mlsanity.com/paper/1804.08150/) (2018)
- [STDP Based Pruning of Connections and Weight Quantization in Spiking Neural Networks for Energy Efficient Recognition](https://mlsanity.com/paper/1710.04734/) (2017)
- [BindsNET: A machine learning-oriented spiking neural networks library in Python](https://mlsanity.com/paper/1806.01423/) (2018)
- [Optimizing the energy consumption of spiking neural networks for neuromorphic applications](https://mlsanity.com/paper/1912.01268/) (2019)
- [SpikeDyn: A Framework for Energy-Efficient Spiking Neural Networks with Continual and Unsupervised Learning Capabilities in Dynamic Environments](https://mlsanity.com/paper/2103.00424/) (2021)
- [An Efficient Spiking Neural Network for Recognizing Gestures with a DVS Camera on the Loihi Neuromorphic Processor](https://mlsanity.com/paper/2006.09985/) (2020)
- [SpykeTorch: Efficient Simulation of Convolutional Spiking Neural Networks with at most one Spike per Neuron](https://mlsanity.com/paper/1903.02440/) (2019)
- [NeuroAttack: Undermining Spiking Neural Networks Security through Externally Triggered Bit-Flips](https://mlsanity.com/paper/2005.08041/) (2020)
- [SparkXD: A Framework for Resilient and Energy-Efficient Spiking Neural Network Inference using Approximate DRAM](https://mlsanity.com/paper/2103.00421/) (2021)
- [Unsupervised Learning with Self-Organizing Spiking Neural Networks](https://mlsanity.com/paper/1807.09374/) (2018)
- [Stochastic rounding and reduced-precision fixed-point arithmetic for solving neural ordinary differential equations](https://mlsanity.com/paper/1904.11263/) (2019)
- [Locally Connected Spiking Neural Networks for Unsupervised Feature Learning](https://mlsanity.com/paper/1904.06269/) (2019)
- [STDP Learning of Image Patches with Convolutional Spiking Neural Networks](https://mlsanity.com/paper/1808.08173/) (2018)
- [Lattice Map Spiking Neural Networks (LM-SNNs) for Clustering and Classifying Image Data](https://mlsanity.com/paper/1906.11826/) (2019)

## Built on by (most cited first, 30 of 37)

- [ReSpawn: Energy-Efficient Fault-Tolerance for Spiking Neural Networks considering Unreliable Memories](https://mlsanity.com/paper/2108.10271/) (2021)
- [lpSpikeCon: Enabling Low-Precision Spiking Neural Network Processing for Efficient Unsupervised Continual Learning on Autonomous Agents](https://mlsanity.com/paper/2205.12295/) (2022)
- [Towards Energy-Efficient and Secure Edge AI: A Cross-Layer Framework](https://mlsanity.com/paper/2109.09829/) (2021)
- [SpikeNAS: A Fast Memory-Aware Neural Architecture Search Framework for Spiking Neural Network-based Embedded AI Systems](https://mlsanity.com/paper/2402.11322/) (2024)
- [MINT: Multiplier-less INTeger Quantization for Energy Efficient Spiking Neural Networks](https://mlsanity.com/paper/2305.09850/) (2023)
- [Continual Learning with Neuromorphic Computing: Foundations, Methods, and Emerging Applications](https://mlsanity.com/paper/2410.09218/) (2024)
- [QSViT: A Methodology for Quantizing Spiking Vision Transformers](https://mlsanity.com/paper/2504.00948/) (2025)
- [Embodied Neuromorphic Artificial Intelligence for Robotics: Perspectives, Challenges, and Research Development Stack](https://mlsanity.com/paper/2404.03325/) (2024)
- [EnforceSNN: Enabling Resilient and Energy-Efficient Spiking Neural Network Inference considering Approximate DRAMs for Embedded Systems](https://mlsanity.com/paper/2304.04039/) (2023)
- [RescueSNN: Enabling Reliable Executions on Spiking Neural Network Accelerators under Permanent Faults](https://mlsanity.com/paper/2304.04041/) (2023)
- [Efficient Deployment of Spiking Neural Networks on SpiNNaker2 for DVS Gesture Recognition Using Neuromorphic Intermediate Representation](https://mlsanity.com/paper/2504.06748/) (2025)
- [Mantis: Enabling Energy-Efficient Autonomous Mobile Agents with Spiking Neural Networks](https://mlsanity.com/paper/2212.12620/) (2022)
- [A Method for Optimizing Connections in Differentiable Logic Gate Networks](https://mlsanity.com/paper/2507.06173/) (2025)
- [Navigating Local Minima in Quantized Spiking Neural Networks](https://mlsanity.com/paper/2202.07221/) (2022)
- [SNN4Agents: A Framework for Developing Energy-Efficient Embodied Spiking Neural Networks for Autonomous Agents](https://mlsanity.com/paper/2404.09331/) (2024)
- [Enabling Efficient Processing of Spiking Neural Networks with On-Chip Learning on Commodity Neuromorphic Processors for Edge AI Systems](https://mlsanity.com/paper/2504.00957/) (2025)
- [tinySNN: Towards Memory- and Energy-Efficient Spiking Neural Networks](https://mlsanity.com/paper/2206.08656/) (2022)
- [Low Precision Quantization-aware Training in Spiking Neural Networks with Differentiable Quantization Function](https://mlsanity.com/paper/2305.19295/) (2023)
- [SpikeExplorer: hardware-oriented Design Space Exploration for Spiking Neural Networks on FPGA](https://mlsanity.com/paper/2404.03714/) (2024)
- [FireFly-S: Exploiting Dual-Side Sparsity for Spiking Neural Networks Acceleration with Reconfigurable Spatial Architecture](https://mlsanity.com/paper/2408.15578/) (2024)
- [QSLM: A Performance- and Memory-aware Quantization Framework with Tiered Search Strategy for Spike-driven Language Models](https://mlsanity.com/paper/2601.00679/) (2026)
- [SpiKernel: A Kernel Size Exploration Methodology for Improving Accuracy of the Embedded Spiking Neural Network Systems](https://mlsanity.com/paper/2404.01685/) (2024)
- [SQUAT: Stateful Quantization-Aware Training in Recurrent Spiking Neural Networks](https://mlsanity.com/paper/2404.19668/) (2024)
- [Direct Training Needs Regularisation: Anytime Optimal Inference Spiking Neural Network](https://mlsanity.com/paper/2405.00699/) (2024)
- [Trimming Down Large Spiking Vision Transformers via Heterogeneous Quantization Search](https://mlsanity.com/paper/2412.05505/) (2024)
- [On the Privacy-Preserving Properties of Spiking Neural Networks with Unique Surrogate Gradients and Quantization Levels](https://mlsanity.com/paper/2502.18623/) (2025)
- [Fully Trainable Deep Differentiable Logic Gate Networks and Lookup Table Networks](https://mlsanity.com/paper/2607.09399/) (2026)
- [The Hardware Impact of Quantization and Pruning for Weights in Spiking Neural Networks](https://mlsanity.com/paper/2302.04174/) (2023)
- [Security-Aware Approximate Spiking Neural Networks](https://mlsanity.com/paper/2301.05264/) (2023)
- [Towards Zero Memory Footprint Spiking Neural Network Training](https://mlsanity.com/paper/2308.08649/) (2023)

## Abstract (arXiv)

A prominent technique for reducing the memory footprint of Spiking Neural Networks (SNNs) without decreasing the accuracy significantly is quantization. However, the state-of-the-art only focus on employing the weight quantization directly from a specific quantization scheme, i.e., either the post-training quantization (PTQ) or the in-training quantization (ITQ), and do not consider (1) quantizing other SNN parameters (e.g., neuron membrane potential), (2) exploring different combinations of quantization approaches (i.e., quantization schemes, precision levels, and rounding schemes), and (3) selecting the SNN model with a good memory-accuracy trade-off at the end. Therefore, the memory saving offered by these state-of-the-art to meet the targeted accuracy is limited, thereby hindering processing SNNs on the resource-constrained systems (e.g., the IoT-Edge devices). Towards this, we propose Q-SpiNN, a novel quantization framework for memory-efficient SNNs. The key mechanisms of the Q-SpiNN are: (1) employing quantization for different SNN parameters based on their significance to the accuracy, (2) exploring different combinations of quantization schemes, precision levels, and rounding schemes to find efficient SNN model candidates, and (3) developing an algorithm that quantifies the benefit of the memory-accuracy trade-off obtained by the candidates, and selects the Pareto-optimal one. The experimental results show that, for the unsupervised network, the Q-SpiNN reduces the memory footprint by ca. 4x, while maintaining the accuracy within 1% from the baseline on the MNIST dataset. For the supervised network, the Q-SpiNN reduces the memory by ca. 2x, while keeping the accuracy within 2% from the baseline on the DVS-Gesture dataset.