Efficient Deep Spiking Multilayer Perceptrons With Multiplication-Free Inference

Boyan Li1; Luziwei Leng2; Shuaijie Shen1; Kaixuan Zhang1; Jianguo Zhang1; Jianxing Liao2; Ran Cheng1

2024

10.1109/TNNLS.2024.3394837

IEEE Transactions on Neural Networks and Learning Systems   影响因子和分区

2162-2388

Advancements in adapting deep convolution architectures for spiking neural networks (SNNs) have significantly enhanced image classification performance and reduced computational burdens. However, the inability of multiplication-free inference (MFI) to align with attention and transformer mechanisms, which are critical to superior performance on high-resolution vision tasks, imposes limitations on these gains. To address this, our research explores a new pathway, drawing inspiration from the progress made in multilayer perceptrons (MLPs). We propose an innovative spiking MLP architecture that uses batch normalization (BN) to retain MFI compatibility and introduce a spiking patch encoding (SPE) layer to enhance local feature extraction capabilities. As a result, we establish an efficient multistage spiking MLP network that blends effectively global receptive fields with local feature extraction for comprehensive spike-based computation. Without relying on pretraining or sophisticated SNN training techniques, our network secures a top-one accuracy of 66.39% on the ImageNet-1K dataset, surpassing the directly trained spiking ResNet-34 by 2.67%. Furthermore, we curtail computational costs, model parameters, and simulation steps. An expanded version of our network compares with the performance of the spiking VGG-16 network with a 71.64% top-one accuracy, all while operating with a model capacity 2.1 times smaller. Our findings highlight the potential of our deep SNN architecture in effectively integrating global and local learning abilities. Interestingly, the trained receptive field in our network mirrors the activity patterns of cortical cells.

SCI ; EI

第一

1.Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China
2.Advanced Computing and Storage Laboratory, Huawei Technologies Company Ltd, Shenzhen, China

Boyan Li,Luziwei Leng,Shuaijie Shen,et al. Efficient Deep Spiking Multilayer Perceptrons With Multiplication-Free Inference[J]. IEEE Transactions on Neural Networks and Learning Systems,2024,PP(99).

Boyan Li.,Luziwei Leng.,Shuaijie Shen.,Kaixuan Zhang.,Jianguo Zhang.,...&Ran Cheng.(2024).Efficient Deep Spiking Multilayer Perceptrons With Multiplication-Free Inference.IEEE Transactions on Neural Networks and Learning Systems,PP(99).

Boyan Li,et al."Efficient Deep Spiking Multilayer Perceptrons With Multiplication-Free Inference".IEEE Transactions on Neural Networks and Learning Systems PP.99(2024).