Reconsidering the energy efficiency of spiking neural networks

• URL: http://arxiv.org/abs/2409.08290v1
• Date: Thu, 29 Aug 2024 07:00:35 GMT
• Title: Reconsidering the energy efficiency of spiking neural networks
• Authors: Zhanglu Yan, Zhenyu Bai, Weng-Fai Wong,
• Abstract summary: Spiking neural networks (SNNs) are generally regarded as more energy-efficient because they do not use multiplications. We present a comparison of the energy consumption of artificial neural networks (ANNs) and SNNs from a hardware perspective.
• Score: 4.37952937111446
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Spiking neural networks (SNNs) are generally regarded as more energy-efficient because they do not use multiplications. However, most SNN works only consider the counting of additions to evaluate energy consumption, neglecting other overheads such as memory accesses and data movement operations. This oversight can lead to a misleading perception of efficiency, especially when state-of-the-art SNN accelerators operate with very small time window sizes. In this paper, we present a detailed comparison of the energy consumption of artificial neural networks (ANNs) and SNNs from a hardware perspective. We provide accurate formulas for energy consumption based on classical multi-level memory hierarchy architectures, commonly used neuromorphic dataflow architectures, and our proposed improved spatial-dataflow architecture. Our research demonstrates that to achieve comparable accuracy and greater energy efficiency than ANNs, SNNs require strict limitations on both time window size T and sparsity s. For instance, with the VGG16 model and a fixed T of 6, the neuron sparsity rate must exceed 93% to ensure energy efficiency across most architectures. Inspired by our findings, we explore strategies to enhance energy efficiency by increasing sparsity. We introduce two regularization terms during training that constrain weights and activations, effectively boosting the sparsity rate. Our experiments on the CIFAR-10 dataset, using T of 6, show that our SNNs consume 69% of the energy used by optimized ANNs on spatial-dataflow architectures, while maintaining an SNN accuracy of 94.18%. This framework, developed using PyTorch, is publicly available for use and further research.

Related papers

• LightSNN: Lightweight Architecture Search for Sparse and Accurate Spiking Neural Networks [1.0485739694839666]
  Spiking Neural Networks (SNNs) are highly regarded for their energy efficiency, inherent activation sparsity, and suitability for real-time processing in edge devices. Most current SNN methods adopt architectures resembling traditional artificial neural networks (ANNs) leading to suboptimal performance when applied to SNNs. We present LightSNN, a rapid and efficient Neural Network Architecture Search (NAS) technique specifically tailored for SNNs.
  arXiv  Detail & Related papers  (2025-03-27T16:38:13Z)
• Differential Coding for Training-Free ANN-to-SNN Conversion [45.70141988713627]
  Spiking Neural Networks (SNNs) exhibit significant potential due to their low energy consumption. converting Artificial Neural Networks (ANNs) to SNNs is an efficient way to achieve high-performance SNNs. This article introduces differential coding for ANN-to-SNN conversion, a novel coding scheme that reduces spike counts and energy consumption.
  arXiv  Detail & Related papers  (2025-03-01T02:17:35Z)
• NeuroNAS: Enhancing Efficiency of Neuromorphic In-Memory Computing for Intelligent Mobile Agents through Hardware-Aware Spiking Neural Architecture Search [6.006032394972252]
  Spiking Neural Networks (SNNs) leverage event-based computation to enable ultra-low power/energy machine learning algorithms. NeuroNAS is a novel framework for developing energy-efficient neuromorphic IMC for intelligent mobile agents.
  arXiv  Detail & Related papers  (2024-06-30T09:51:58Z)
• SparrowSNN: A Hardware/software Co-design for Energy Efficient ECG Classification [7.030659971563306]
  spiking neural networks (SNNs) are well-known for their energy efficiency. sparrowSNN achieves a state-of-the-art accuracy of 98.29% for SNNs, with energy consumption of 31.39nJ per inference and power usage of 6.1uW.
  arXiv  Detail & Related papers  (2024-05-06T10:30:05Z)
• Continuous Spiking Graph Neural Networks [43.28609498855841]
  Continuous graph neural networks (CGNNs) have garnered significant attention due to their ability to generalize existing discrete graph neural networks (GNNs) We introduce the high-order structure of COS-GNN, which utilizes the second-order ODE for spiking representation and continuous propagation. We provide the theoretical proof that COS-GNN effectively mitigates the issues of exploding and vanishing gradients, enabling us to capture long-range dependencies between nodes.
  arXiv  Detail & Related papers  (2024-04-02T12:36:40Z)
• LitE-SNN: Designing Lightweight and Efficient Spiking Neural Network through Spatial-Temporal Compressive Network Search and Joint Optimization [48.41286573672824]
  Spiking Neural Networks (SNNs) mimic the information-processing mechanisms of the human brain and are highly energy-efficient. We propose a new approach named LitE-SNN that incorporates both spatial and temporal compression into the automated network design process.
  arXiv  Detail & Related papers  (2024-01-26T05:23:11Z)
• Pursing the Sparse Limitation of Spiking Deep Learning Structures [42.334835610250714]
  Spiking Neural Networks (SNNs) are garnering increased attention for their superior computation and energy efficiency. We introduce an innovative algorithm capable of simultaneously identifying both weight and patch-level winning tickets. We demonstrate that our spiking lottery ticket achieves comparable or superior performance even when the model structure is extremely sparse.
  arXiv  Detail & Related papers  (2023-11-18T17:00:40Z)
• Adaptive-SpikeNet: Event-based Optical Flow Estimation using Spiking Neural Networks with Learnable Neuronal Dynamics [6.309365332210523]
  Spiking Neural Networks (SNNs) with their neuro-inspired event-driven processing can efficiently handle asynchronous data. We propose an adaptive fully-spiking framework with learnable neuronal dynamics to alleviate the spike vanishing problem. Our experiments on datasets show an average reduction of 13% in average endpoint error (AEE) compared to state-of-the-art ANNs.
  arXiv  Detail & Related papers  (2022-09-21T21:17:56Z)
• Weightless Neural Networks for Efficient Edge Inference [1.7882696915798877]
  Weightless Neural Networks (WNNs) are a class of machine learning model which use table lookups to perform inference. We propose a novel WNN architecture, BTHOWeN, with key algorithmic and architectural improvements over prior work. BTHOWeN targets the large and growing edge computing sector by providing superior latency and energy efficiency.
  arXiv  Detail & Related papers  (2022-03-03T01:46:05Z)
• Keys to Accurate Feature Extraction Using Residual Spiking Neural Networks [1.101002667958165]
  Spiking neural networks (SNNs) have become an interesting alternative to conventional artificial neural networks (ANNs) We present a study on the key components of modern spiking architectures. We design a spiking version of the successful residual network (ResNet) architecture and test different components and training strategies on it.
  arXiv  Detail & Related papers  (2021-11-10T21:29:19Z)
• Neural network relief: a pruning algorithm based on neural activity [47.57448823030151]
  We propose a simple importance-score metric that deactivates unimportant connections. We achieve comparable performance for LeNet architectures on MNIST. The algorithm is not designed to minimize FLOPs when considering current hardware and software implementations.
  arXiv  Detail & Related papers  (2021-09-22T15:33:49Z)
• DTNN: Energy-efficient Inference with Dendrite Tree Inspired Neural Networks for Edge Vision Applications [2.1800759000607024]
  We propose Dendrite-Tree based Neural Network (DTNN) for energy-efficient inference with table lookup operations enabled by activation quantization. DTNN achieved significant energy saving (19.4X and 64.9X improvement on ResNet-18 and VGG-11 with ImageNet, respectively) with negligible loss of accuracy.
  arXiv  Detail & Related papers  (2021-05-25T11:44:12Z)
• ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training [68.63354877166756]
  ActNN is a memory-efficient training framework that stores randomly quantized activations for back propagation. ActNN reduces the memory footprint of the activation by 12x, and it enables training with a 6.6x to 14x larger batch size.
  arXiv  Detail & Related papers  (2021-04-29T05:50:54Z)
• SmartExchange: Trading Higher-cost Memory Storage/Access for Lower-cost Computation [97.78417228445883]
  We present SmartExchange, an algorithm- hardware co-design framework for energy-efficient inference of deep neural networks (DNNs) We develop a novel algorithm to enforce a specially favorable DNN weight structure, where each layerwise weight matrix can be stored as the product of a small basis matrix and a large sparse coefficient matrix whose non-zero elements are all power-of-2. We further design a dedicated accelerator to fully utilize the SmartExchange-enforced weights to improve both energy efficiency and latency performance.
  arXiv  Detail & Related papers  (2020-05-07T12:12:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.