MAP-SNN: Mapping spike activities with multiplicity, adaptability, and plasticity into bio-plausible spiking neural networks

Chengting Yu; Yangkai Du; Mufeng Chen; Aili Wang; Gaoang Wang; Erping Li

doi:10.3389/fnins.2022.945037

MAP-SNN: Mapping spike activities with multiplicity, adaptability, and plasticity into bio-plausible spiking neural networks

Front Neurosci. 2022 Sep 20:16:945037. doi: 10.3389/fnins.2022.945037. eCollection 2022.

Authors

Chengting Yu^{1

2}, Yangkai Du³, Mufeng Chen¹, Aili Wang^{1

2}, Gaoang Wang², Erping Li^{1

2}

Affiliations

¹ College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China.
² Zhejiang University - University of Illinois at Urbana-Champaign Institute, Zhejiang University, Haining, China.
³ College of Computer Science and Technology, Zhejiang University, Hangzhou, China.

Abstract

Spiking Neural Networks (SNNs) are considered more biologically realistic and power-efficient as they imitate the fundamental mechanism of the human brain. Backpropagation (BP) based SNN learning algorithms that utilize deep learning frameworks have achieved good performance. However, those BP-based algorithms partially ignore bio-interpretability. In modeling spike activity for biological plausible BP-based SNNs, we examine three properties: multiplicity, adaptability, and plasticity (MAP). Regarding multiplicity, we propose a Multiple-Spike Pattern (MSP) with multiple-spike transmission to improve model robustness in discrete time iterations. To realize adaptability, we adopt Spike Frequency Adaption (SFA) under MSP to reduce spike activities for enhanced efficiency. For plasticity, we propose a trainable state-free synapse that models spike response current to increase the diversity of spiking neurons for temporal feature extraction. The proposed SNN model achieves competitive performances on the N-MNIST and SHD neuromorphic datasets. In addition, experimental results demonstrate that the proposed three aspects are significant to iterative robustness, spike efficiency, and the capacity to extract spikes' temporal features. In summary, this study presents a realistic approach for bio-inspired spike activity with MAP, presenting a novel neuromorphic perspective for incorporating biological properties into spiking neural networks.

Keywords: backpropagation (BP); leaky integrate-and-fire (LIF) neuron; multiple spike pattern (MSP); neuromorphic recognition; spike frequency adaption (SFA); spiking neural network (SNN); state-free synaptic response model (SFSRM).