SDenseNet-An Improved DenseNet Model for Spiking Neural Networks

Abstract

Abstract In order to port DenseNet to a spiking neural network, its activation function must be modified to spiking neurons. In addition, the direct conversion model suffers from the inability to transmit non-peak sequences across layers and a sluggish training pace. A deep convolutional spiking neural network (DCSNN) architecture called SDenseNet has been designed in order to address these problems. The first step is to adjust the connection sequence of each module layer in the network to ensure that the output of each layer is the spiking sequence; Next, convolutional kernels of different sizes are used in parallel in the Transition layer to extract different features and spliced along the length of the channel in an attempt to build up the performance of the feature extraction. The framework suggested in this paper has demonstrated improvement in benchmark indicators such as training speed, accuracy rate, and mean loss when compared to the framework directly converted to the spiking neural network by training the two publicly image data sets named CIFAR-10 and CIFAR-100.