Abstract: The dynamic threshold learning algorithm of Spiking  neurons can change the size of the threshold during the training process, which can effectively improve the noise resistance of neurons. However, the use of dynamic thresholds can reduce the learning accuracy of neurons and easily cause neuron silence when combining with the gradient-based learning algorithm. To address this issue, an improved gradient-based noise-resistant learning algorithm with high and low thresholds is proposed. This algorithm uses high and low thresholds to avoid loss of learning accuracy and uses virtual excitation pulses to continue the learning process when neurons are silent. At the same time, a dynamic learning rate is used to reduce the impact of high and low thresholds on the learning cycle. The experimental results show that this algorithm can significantly improve the noise resistance of neurons while ensuring learning accuracy and convergence speed. It is well suited for the pulse neuron learning algorithm based on gradient descent.

Key words: spiking neuron, high and low thresholds, gradient descent, anti-noise capability