STCSNN: High energy efficiency spike-train level spiking neural networks with spatio-temporal conversion
arXiv:2307.07136 · doi:10.1016/j.neucom.2024.128364
Abstract
Brain-inspired spiking neuron networks (SNNs) have attracted widespread research interest due to their low power features, high biological plausibility, and strong spatiotemporal information processing capability. Although adopting a surrogate gradient (SG) makes the non-differentiability SNN trainable, achieving comparable accuracy for ANNs and keeping low-power features simultaneously is still tricky. In this paper, we proposed an energy-efficient spike-train level spiking neural network with spatio-temporal conversion, which has low computational cost and high accuracy. In the STCSNN, spatio-temporal conversion blocks (STCBs) are proposed to keep the low power features of SNNs and improve accuracy. However, STCSNN cannot adopt backpropagation algorithms directly due to the non-differentiability nature of spike trains. We proposed a suitable learning rule for STCSNNs by deducing the equivalent gradient of STCB. We evaluate the proposed STCSNN on static and neuromorphic datasets, including Fashion-Mnist, Cifar10, Cifar100, TinyImageNet, and DVS-Cifar10. The experiment results show that our proposed STCSNN outperforms the state-of-the-art accuracy on nearly all datasets, using fewer time steps and being highly energy-efficient.
Accepted by Neurocomputing on 10 August 2024
References in corpus (6)
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- Temporal Efficient Training of Spiking Neural Network via Gradient Re-weighting
- Theory and Tools for the Conversion of Analog to Spiking Convolutional Neural Networks
- Spikingformer: A Key Foundation Model for Spiking Neural Networks
- Towards Low-Latency Energy-Efficient Deep SNNs via Attention-Guided Compression
- Ultra-low Latency Adaptive Local Binary Spiking Neural Network with Accuracy Loss Estimator