Redundant information transfer in a neural network can increase the complexity of the deep learning model, thus increasing its power consumption. We introduce in this paper a novel spiking neuron, termed Variable Spiking Neuron (VSN), which can reduce the redundant firing using lessons from biological neuron inspired Leaky Integrate and Fire Spiking Neurons (LIF-SN). The proposed VSN blends LIF-SN and artificial neurons. It garners the advantage of intermittent firing from the LIF-SN and utilizes the advantage of continuous activation from the artificial neuron. This property of the proposed VSN makes it suitable for regression tasks, which is a weak point for the vanilla spiking neurons, all while keeping the energy budget low. The proposed VSN is tested against both classification and regression tasks. The results produced advocate favorably towards the efficacy of the proposed spiking neuron, particularly for regression tasks.

本论文介绍了一种称为变量尖峰神经元（VSN）的新型尖峰神经元，它可以通过借鉴生物神经元的漏积分与发射尖峰神经元（LIF-SN）的概念，减少冗余激发，同时保持能源预算低，并在分类和回归任务中取得了良好的结果。

神经科学启发的科学机器学习 (第一部分): 变量尖峰神经元用于回归