paper-with-me

홈 › Papers

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

2022-06-17 · Rachmad Vidya Wicaksana Putra, Muhammad Shafique

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.

📄 PDF Abstract BibTeX arXiv:2206.08656

Code (0)

등록된 구현이 없습니다.

Tasks

Quantization

Similar Papers 제목 키워드 기반

Computing with hardware neurons: spiking or classical? Perspectives of applied Spiking Neural Networks from the hardware side

2016-02-05 · Sergei Dytckov, Masoud Daneshtalab

While classical neural networks take a position of a leading method in the machine learning community, spiking neuromorphic systems bring attention and large projects in neuroscience. Spiking neural networks were shown t…

High-Performance Temporal Reversible Spiking Neural Networks with $O(L)$ Training Memory and $O(1)$ Inference Cost

2024-05-26 · Jiakui Hu, Man Yao, Xuerui Qiu, Yuhong Chou 외

Multi-timestep simulation of brain-inspired Spiking Neural Networks (SNNs) boost memory requirements during training and increase inference energy cost. Current training methods cannot simultaneously solve both training …

Neural Dynamics Self-Attention for Spiking Transformers

2026-03-09 · Dehao Zhang, Fukai Guo, Shuai Wang, Jingya Wang 외 arxiv

Integrating Spiking Neural Networks (SNNs) with Transformer architectures offers a promising pathway to balance energy efficiency and performance, particularly for edge vision applications. However, existing Spiking Tran…

Ge$^\text{2}$mS-T: Multi-Dimensional Grouping for Ultra-High Energy Efficiency in Spiking Transformer

2026-04-10 · Zecheng Hao, Shenghao Xie, Kang Chen, Wenxuan Liu 외 arxiv

Spiking Neural Networks (SNNs) offer superior energy efficiency over Artificial Neural Networks (ANNs). However, they encounter significant deficiencies in training and inference metrics when applied to Spiking Vision Tr…

Adversarially Robust Spiking Neural Networks with Sparse Connectivity

2025-05-16 · Mathias Schmolli, Maximilian Baronig, Robert Legenstein, Ozan Özdenizci

Deployment of deep neural networks in resource-constrained embedded systems requires innovative algorithmic solutions to facilitate their energy and memory efficiency. To further ensure the reliability of these systems a…

Adversarial Robustness