DynSNN: A Dynamic Approach to Reduce Redundancy in Spiking Neural Networks

Current Internet of Things (IoT) embedded applications use machine learning algorithms to process the collected data. However, the computational complexity and storage requirements of existing deep learning methods hinder the wide availability of embedded applications. Spiking Neural Networks~(SNN) is a brain-inspired learning approach that emerged from theoretical neuroscience, as an alternative computing paradigm for enabling low-power computation. Since these IoT devices are usually resource-constrained, compression techniques are crucial in the practical application of SNNs. Most existing methods directly apply pruning methods from artificial neural networks~(ANNs) to SNNs, while ignoring the distinction between ANNs and SNNs, thus inhibiting the potential of pruning methods on SNNs. In this paper, inspired by the topology of neuronal co-activity in the system, we propose a dynamic pruning framework~(dubbed DynSNN) for SNNs, enabling us to seamlessly optimize network topology on the fly almost without accuracy loss. Experimental results on a wide range of classification applications show that the proposed method achieves almost lossless for SNN on MNIST, CIFAR-10, and ImageNet datasets. Moreover, it reaches a $\sim 0.3%$ accuracy loss under $34%$ compression rate on CIFAR and ImageNet, and achieves $60%$ compression rate with no accuracy loss on MNIST, which reveals remarkable structure refining capability in SNNs.