MAP-SNN: Mapping Spike Activities with Multiplicity, Adaptability, and Plasticity into Bio-Plausible Spiking Neural Networks

Abstract

Spiking Neural Network (SNN) is considered more biologically realistic and power-efficient as it imitates the fundamental mechanism of the human brain. Recently, backpropagation (BP) based SNN learning algorithms that utilize deep learning frameworks have achieved good performance. However, bio-interpretability is partially neglected in those BP-based algorithms. Toward bio-plausible BP-based SNNs, we consider three properties in modeling spike activities: Multiplicity, Adaptability, and Plasticity (MAP). In terms of multiplicity, we propose a Multiple-Spike Pattern (MSP) with multiple spike transmission to strengthen model robustness in discrete time-iteration. To realize adaptability, we adopt Spike Frequency Adaption (SFA) under MSP to decrease spike activities for improved efficiency. For plasticity, we propose a trainable convolutional synapse that models spike response current to enhance the diversity of spiking neurons for temporal feature extraction. The proposed SNN model achieves competitive performances on neuromorphic datasets: N-MNIST and SHD. Furthermore, experimental results demonstrate that the proposed three aspects are significant to iterative robustness, spike efficiency, and temporal feature extraction capability of spike activities. In summary, this work proposes a feasible scheme for bio-inspired spike activities with MAP, offering a new neuromorphic perspective to embed biological characteristics into spiking neural networks.

References in corpus (12)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Deep Learning in Spiking Neural Networks
• Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networks
• SLAYER: Spike Layer Error Reassignment in Time
• The Heidelberg spiking datasets for the systematic evaluation of spiking neural networks
• Deep learning incorporating biologically-inspired neural dynamics
• Long short-term memory and learning-to-learn in networks of spiking neurons
• Training dynamically balanced excitatory-inhibitory networks
• Hybrid Macro/Micro Level Backpropagation for Training Deep Spiking Neural Networks
• Acquisition of Visual Features Through Probabilistic Spike-Timing-Dependent Plasticity
• Optimal localist and distributed coding of spatiotemporal spike patterns through STDP and coincidence detection
• Target spiking patterns enable efficient and biologically plausible learning for complex temporal tasks

Cited by in corpus (2)

• STSC-SNN: Spatio-Temporal Synaptic Connection with Temporal Convolution and Attention for Spiking Neural Networks
• Empirical study on the efficiency of Spiking Neural Networks with axonal delays, and algorithm-hardware benchmarking