Spiking Neural Networks with Laterally-Inhibited Self-Recurrent Units
Spiking Neural Networks with Laterally-Inhibited Self-Recurrent Units
复制标题
DOI：
10.1109/ijcnn52387.2021.9533726
复制
发表时间：
2021-07
期刊：
影响因子：
--
通讯作者：
Wenrui Zhang;Peng Li-
中科院分区：
文献类型：
--
作者：
Wenrui Zhang;Peng Li-
在生物大脑中，循环连接在皮质计算、网络动力学调制和通信中起着至关重要的作用。然而，在递归脉冲神经网络（SNNs）中，递归大多是由随机连接构造的。兴奋性和抑制性循环连接如何影响网络反应，以及什么样的连接有益于学习成绩仍然不清楚。在这项工作中，我们提出了一种新的经常性的结构称为横向抑制自我循环单位（LISR），它由一个兴奋性神经元与自我循环连接连接在一起的抑制性神经元通过兴奋性和抑制性突触。兴奋性神经元的自返连接减轻了由放电-重置机制引起的信息丢失，维持了神经元的长时程记忆。从抑制性神经元到相应兴奋性神经元的侧抑制，一方面调节后者的放电活动。另一方面，它作为一个遗忘门，清除兴奋性神经元的记忆。基于神经形态计算中常用的语音和图像数据集，基于所提出的LISR的RSNN比通过具有类似计算成本的最先进的反向传播方法训练的前馈SNN显着提高性能高达9.26%。
In biological brains, recurrent connections play a crucial role in cortical computation, modulation of network dynamics, and communication. However, in recurrent spiking neural networks (SNNs), recurrence is mostly constructed by random connections. How excitatory and inhibitory recurrent connections affect network responses and what kinds of connectivity benefit learning performance is still obscure. In this work, we propose a novel recurrent structure called the Laterally-Inhibited Self-Recurrent Unit (LISR), which consists of one excitatory neuron with a self-recurrent connection wired together with an inhibitory neuron through excitatory and inhibitory synapses. The self-recurrent connection of the excitatory neuron mitigates the information loss caused by the firing-and-resetting mechanism and maintains the long-term neuronal memory. The lateral inhibition from the inhibitory neuron to the corresponding excitatory neuron, on the one hand, adjusts the firing activity of the latter. On the other hand, it plays as a forget gate to clear the memory of the excitatory neuron. Based on speech and image datasets commonly used in neuromorphic computing, RSNNs based on the proposed LISR improve performance significantly by up to 9.26% over feedforward SNNs trained by a state-of-the-art backpropagation method with similar computational costs.