An all integer-based spiking neural network with dynamic threshold adaptation

Front Neurosci. 2024 Dec 17:18:1449020. doi: 10.3389/fnins.2024.1449020. eCollection 2024.

Abstract

Spiking Neural Networks (SNNs) are typically regards as the third generation of neural networks due to their inherent event-driven computing capabilities and remarkable energy efficiency. However, training an SNN that possesses fast inference speed and comparable accuracy to modern artificial neural networks (ANNs) remains a considerable challenge. In this article, a sophisticated SNN modeling algorithm incorporating a novel dynamic threshold adaptation mechanism is proposed. It aims to eliminate the spiking synchronization error commonly occurred in many traditional ANN2SNN conversion works. Additionally, all variables in the proposed SNNs, including the membrane potential, threshold and synaptic weights, are quantized to integers, making them highly compatible with hardware implementation. Experimental results indicate that the proposed spiking LeNet and VGG-Net achieve accuracies exceeding 99.45% and 93.15% on the MNIST and CIFAR-10 datasets, respectively, with only 4 and 8 time steps required for simulating one sample. Due to this all integer-based quantization process, the required computational operations are significantly reduced, potentially providing a substantial energy efficiency advantage for numerous edge computing applications.

Keywords: ANN2SNN conversion; dynamic threshold adaptation; network quantization; neuromorphic computing; spiking neural network.

Grants and funding

The author(s) declare financial support was received for the research, authorship, and/or publication of this article. This work was supported by the National Postdoctoral Research Station of CQBDRI.