计算机技术与发展2018，Vol.28Issue(2)：31-35,5.DOI:10.3969/j.issn.1673-629X.2018.02.008
基于循环卷积神经网络的目标检测与分类
Object Detection and Classification Based on Circular Convolutional Neural Network
摘要
Abstract
Convolutional neural network simulates human vision recognition and extracts the abstract characteristics significantly of the image target,with better effects on the application of image target detection and classification.In the currently popular training of convolution neural network by batch stochastic gradient algorithm,when neurons in a saturated state,there will be a slow gradient descent and excessive fitting which lead to the difficulties in training of the neural network model.In this paper,we propose a simple circular convolutional neural net-works combined with the characteristics of the convolutional and circular neural networks.In the training of circular convolutional neural net-work model,advance and retreat method and golden section are used to adaptively change the normalized parameter and the learning rate of batch stochastic gradient descent algorithm.Experiment shows that the proposed algorithm,with a better effect on detection and classification with faster convergence,can avoid the problem of slow gradient decent and excessive fitting to some extent.关键词
物体检测/进退法/黄金分割算法/随机梯度算法/神经网络Key words
object detection/advance and retreat method/golden section algorithm/stochastic gradient method/neural network分类
信息技术与安全科学引用本文复制引用
艾玲梅,叶雪娜..基于循环卷积神经网络的目标检测与分类[J].计算机技术与发展,2018,28(2):31-35,5.基金项目
国家自然科学基金(61672021) （61672021）
陕西省自然科学基础研究计划资助项目(2015JM6296) （2015JM6296）
