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

arXiv: https://arxiv.org/abs/2206.08656 · HTML: https://mlsanity.com/paper/2206.08656/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 30 references that are in the map.
- First posted on arXiv 17 Jun 2022.

## Builds on (most cited first, 20 of 20)

- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Quantizing deep convolutional networks for efficient inference: A whitepaper](https://mlsanity.com/paper/1806.08342/) (2018)
- [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)
- [T2FSNN: Deep Spiking Neural Networks with Time-to-first-spike Coding](https://mlsanity.com/paper/2003.11741/) (2020)
- [BindsNET: A machine learning-oriented spiking neural networks library in Python](https://mlsanity.com/paper/1806.01423/) (2018)
- [Q-SpiNN: A Framework for Quantizing Spiking Neural Networks](https://mlsanity.com/paper/2107.01807/) (2021)
- [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)
- [SparkXD: A Framework for Resilient and Energy-Efficient Spiking Neural Network Inference using Approximate DRAM](https://mlsanity.com/paper/2103.00421/) (2021)
- [ReSpawn: Energy-Efficient Fault-Tolerance for Spiking Neural Networks considering Unreliable Memories](https://mlsanity.com/paper/2108.10271/) (2021)
- [SoftSNN: Low-Cost Fault Tolerance for Spiking Neural Network Accelerators under Soft Errors](https://mlsanity.com/paper/2203.05523/) (2022)
- [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)
- [ASP: Learning to Forget with Adaptive Synaptic Plasticity in Spiking Neural Networks](https://mlsanity.com/paper/1703.07655/) (2017)
- [ROMANet: Fine-Grained Reuse-Driven Off-Chip Memory Access Management and Data Organization for Deep Neural Network Accelerators](https://mlsanity.com/paper/1902.10222/) (2019)
- [DRMap: A Generic DRAM Data Mapping Policy for Energy-Efficient Processing of Convolutional Neural Networks](https://mlsanity.com/paper/2004.10341/) (2020)
- [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, 3 of 3)

- [LaneSNNs: Spiking Neural Networks for Lane Detection on the Loihi Neuromorphic Processor](https://mlsanity.com/paper/2208.02253/) (2022)
- [Spiking Neural Networks and Bio-Inspired Supervised Deep Learning: A Survey](https://mlsanity.com/paper/2307.16235/) (2023)
- [EnforceSNN: Enabling Resilient and Energy-Efficient Spiking Neural Network Inference considering Approximate DRAMs for Embedded Systems](https://mlsanity.com/paper/2304.04039/) (2023)

## 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.