ALBSNN: ultra-low latency adaptive local binary spiking neural network with accuracy loss estimator

Frontiers in Neuroscience

Neuroscience

Yijian Pei¹  Changqing Xu²  Zili Wu³  Yi Liu⁴  Yintang Yang⁴ 

[1] Guangzhou Institute of Technology, Xidian University, Xi'an, China;Guangzhou Institute of Technology, Xidian University, Xi'an, China;School of Microelectronics, Xidian University, Xi'an, China;School of Computer Science and Technology, Xidian University, Xi'an, China;School of Microelectronics, Xidian University, Xi'an, China;

关键词: spiking neural networks;    binary neural networks;    neuromorphic computing;    sparsity;    visual recognition;   

DOI  :  10.3389/fnins.2023.1225871

 received in 2023-05-20, accepted in 2023-08-24,  发布年份 2023

来源: Frontiers

【 摘 要 】

Spiking neural network (SNN) is a brain-inspired model with more spatio-temporal information processing capacity and computational energy efficiency. However, with the increasing depth of SNNs, the memory problem caused by the weights of SNNs has gradually attracted attention. In this study, we propose an ultra-low latency adaptive local binary spiking neural network (ALBSNN) with accuracy loss estimators, which dynamically selects the network layers to be binarized to ensure a balance between quantization degree and classification accuracy by evaluating the error caused by the binarized weights during the network learning process. At the same time, to accelerate the training speed of the network, the global average pooling (GAP) layer is introduced to replace the fully connected layers by combining convolution and pooling. Finally, to further reduce the error caused by the binary weight, we propose binary weight optimization (BWO), which updates the overall weight by directly adjusting the binary weight. This method further reduces the loss of the network that reaches the training bottleneck. The combination of the above methods balances the network's quantization and recognition ability, enabling the network to maintain the recognition capability equivalent to the full precision network and reduce the storage space by more than 20%. So, SNNs can use a small number of time steps to obtain better recognition accuracy. In the extreme case of using only a one-time step, we still can achieve 93.39, 92.12, and 69.55% testing accuracy on three traditional static datasets, Fashion- MNIST, CIFAR-10, and CIFAR-100, respectively. At the same time, we evaluate our method on neuromorphic N-MNIST, CIFAR10-DVS, and IBM DVS128 Gesture datasets and achieve advanced accuracy in SNN with binary weights. Our network has greater advantages in terms of storage resources and training time.

【 授权许可】

Unknown   
Copyright © 2023 Pei, Xu, Wu, Liu and Yang.