Rethinking Deep Spiking Neural Networks: A Multi-Layer Perceptron Approach

Luziwei Leng, Boyan Li, Ran Cheng, Shuaijie Shen, Kaixuan Zhang, Jianguo Zhang, Jianxing Liao

Keywords: spiking neural network, multi-layer perceptron, image classification

TL;DR: A multi-layer perceptron approach for deep spiking neural network, achieving state-of-the-art results on ImageNet.

Abstract: By adopting deep convolution architectures, spiking neural networks (SNNs) have recently achieved competitive performances with their artificial counterparts in image classification, meanwhile with much lower computation cost due to event-driven and sparse activation. However, the multiplication-free inference (MFI) principle makes SNNs incompatible with attention or transformer mechanisms which have shown significant performance gains on high resolution vision tasks. Inspired from recent works on multi-layer perceptrons (MLPs), we explore an efficient spiking MLP design using batch normalization instead of layer normalization in both the token and the channel block to be compatible with MFI. We further strengthen the network’s local feature learning ability with a spiking patch encoding layer, which significantly improves the network performance. Based on these building blocks, we explore an optimal skip connection configuration and develop an efficient multi-stage spiking MLP network combining global receptive field and local feature extraction, achieving full spike-based computation. Without pre-training or other advanced SNN training techniques, the spiking MLP network achieves 66.39% top-1 accuracy on the ImageNet-1K dataset, surpassing the state-of-the-art directly trained spiking ResNet-34 by 2.67% under similar model capacity meanwhile with shorter simulation steps and much less computation cost. Another larger variant of the network achieves 68.84% top-1 accuracy, rivaling the spiking VGG-16 network with 4 times smaller model capacity. Our work demonstrates the effectiveness of an alternative deep SNN architecture combining both global and local learning abilities. More interestingly, finally we show a close resemblance of the trained receptive field of our network to cells in the cortex. Code will be publicly available.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Neuroscience and Cognitive Science (e.g., neural coding, brain-computer interfaces)