脉冲非对称卷积神经网络的图像与事件分类算法
Image and event classification algorithm based on spike aymmetric convolutional neural network
桑林1
作者信息
- 1. 黑龙江科技大学 创新创业学院,哈尔滨 150022
- 折叠
摘要
为了提升模型性能的同时不引入额外的计算量与能量消耗,提出了一种脉冲非对称卷积算法.利用卷积核交叉部分的权重大的特点,采用多个尺寸的卷积核替换普通卷积的单个卷积核进行卷积运算与叠加,提高中心卷积核的决策作用,在推理阶段将脉冲非对称卷积层和批量归一化层进行合并,实现简化运算.结果表明,基于脉冲非对称卷积算法的图像与事件分类模型在DVS Gesture数据集上分类精度可达98.1%,同时不引入额外的计算量和能耗.
Abstract
This paper proposes a spiking asymmetric convolution algorithm to enhance model per-formance without introducing additional computational complexity and energy consumption.The study is accomplished by using multiple-sized convolution kernels to replace a single convolution kernel of ordina-ry convolution for convolution operating and superposing based on the greater weight of the cross-part of convolution kernels aiming to improve the decision-making role of the central convolution kernel;and merging the spiking asymmetric convolutional layers with batch normalization layers to simplify computa-tions during inference.The results demonstrate that the image and event classification models based on the spiking asymmetric convolution algorithm achieve a classification accuracy of 98.1% on DVS Gesture dataset,without introducing additional computational complexity and energy consumption.
关键词
脉冲神经网络/类脑计算/残差学习/非对称卷积Key words
spiking neural networks/neuromorphic computing/residual learning/asymmetric con-volution引用本文复制引用
出版年
2024
国家科技期刊平台
NSTL
维普
万方数据