mlsanityData to 7 Oct 2026

tinySNN: Towards Memory- and Energy-Efficient Spiking Neural Networks

arXiv 2206.08656 ↗First posted 17 Jun 2022cs.NE cs.AI cs.ARcited by 3

Not on the map. Why?

Abstract (arXiv)

Larger Spiking Neural Network (SNN) models are typically favorable as they can offer higher accuracy. However, employing such models on the resource- and energy-constrained embedded platforms is inefficient. Towards this, we present a tinySNN framework that optimizes the memory and energy requirements of SNN processing in both the training and inference phases, while keeping the accuracy high. It is achieved by reducing the SNN operations, improving the learning quality, quantizing the SNN parameters, and selecting the appropriate SNN model. Furthermore, our tinySNN quantizes different SNN parameters (i.e., weights and neuron parameters) to maximize the compression while exploring different combinations of quantization schemes, precision levels, and rounding schemes to find the model that provides acceptable accuracy. The experimental results demonstrate that our tinySNN significantly reduces the memory footprint and the energy consumption of SNNs without accuracy loss as compared to the baseline network. Therefore, our tinySNN effectively compresses the given SNN model to achieve high accuracy in a memory- and energy-efficient manner, hence enabling the employment of SNNs for the resource- and energy-constrained embedded applications.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 20 of its 30 references that are in the map. First posted on arXiv 17 Jun 2022.

Builds on

20 of 30 references.

References · 20

  1. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  2. 2018Quantizing deep convolutional networks for efficient inference: A whitepapercited by 507
  3. 2018Deep Learning in Spiking Neural Networkscited by 258
  4. 2020T2FSNN: Deep Spiking Neural Networks with Time-to-first-spike Codingcited by 45
  5. 2018BindsNET: A machine learning-oriented spiking neural networks library in Pythoncited by 42
  6. 2017STDP Based Pruning of Connections and Weight Quantization in Spiking Neural Networks for Energy Efficient Recognitioncited by 41
  7. 2021Q-SpiNN: A Framework for Quantizing Spiking Neural Networkscited by 33
  8. 2021SpikeDyn: A Framework for Energy-Efficient Spiking Neural Networks with Continual and Unsupervised Learning Capabilities in Dynamic Environmentscited by 29
  9. 2021SparkXD: A Framework for Resilient and Energy-Efficient Spiking Neural Network Inference using Approximate DRAMcited by 21
  10. 2021ReSpawn: Energy-Efficient Fault-Tolerance for Spiking Neural Networks considering Unreliable Memoriescited by 20
  11. 2022SoftSNN: Low-Cost Fault Tolerance for Spiking Neural Network Accelerators under Soft Errorscited by 18
  12. 2022lpSpikeCon: Enabling Low-Precision Spiking Neural Network Processing for Efficient Unsupervised Continual Learning on Autonomous Agentscited by 18
8 more
  1. 2021Towards Energy-Efficient and Secure Edge AI: A Cross-Layer Frameworkcited by 17
  2. 2017ASP: Learning to Forget with Adaptive Synaptic Plasticity in Spiking Neural Networkscited by 15
  3. 2019ROMANet: Fine-Grained Reuse-Driven Off-Chip Memory Access Management and Data Organization for Deep Neural Network Acceleratorscited by 11
  4. 2020DRMap: A Generic DRAM Data Mapping Policy for Energy-Efficient Processing of Convolutional Neural Networkscited by 11
  5. 2019Stochastic rounding and reduced-precision fixed-point arithmetic for solving neural ordinary differential equationscited by 10
  6. 2019Locally Connected Spiking Neural Networks for Unsupervised Feature Learningcited by 9
  7. 2018STDP Learning of Image Patches with Convolutional Spiking Neural Networkscited by 8
  8. 2019Lattice Map Spiking Neural Networks (LM-SNNs) for Clustering and Classifying Image Datacited by 7

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 2.

3 papers.

  1. 2022LaneSNNs: Spiking Neural Networks for Lane Detection on the Loihi Neuromorphic Processorcited by 10
  2. 2023Spiking Neural Networks and Bio-Inspired Supervised Deep Learning: A Surveycited by 8
  3. 2023EnforceSNN: Enabling Resilient and Energy-Efficient Spiking Neural Network Inference considering Approximate DRAMs for Embedded Systemscited by 6