摘要
提出了一种联合卷积和递归神经网络的深层网络结构,在卷积神经网络中引入了递归神经网络能学到的组合特征:原始图片先通过一级由k均值聚类学得滤波器的卷积神经网络,得到的结果再同时通过一级卷积和一级递归神经网络,最后得到的特征向量由Softmax分类器进行分类。实验结果表明:在第二级卷积和递归神经网络权重随机的情况下,该网络的识别率已经能够达到98.28%,跟其他网络结构相比,大大减少了训练时间,而且无需复杂的工程技巧。
Propose a joint convolutional and recursive neural network structure, bring the combinational feature that recursive neural networks can learn into convolutional neural networks, that is, the raw image is first passed through a convolutional neural network stage with filters trained by k-means clustering, the result is then passed through a convolutional and a recursive neural network stage simultaneously, at last ,the obtained feature vector is classified by softmax classifier. Experimental result shows that even with weights randomly set for the second convolutional and recursive neural network, the network reaches a recognition rate of 98.28 % , compared to other network structures, it greatly reduces training time and requires no complex engineering tricks.
出处
《传感器与微系统》
CSCD
北大核心
2014年第8期30-33,共4页
Transducer and Microsystem Technologies
关键词
卷积神经网络
递归神经网络
K均值聚类
convolutional neural networks
recursive neural networks
k-means clustering
作者简介
宣森炎（1988-），男，浙江诸暨人，硕士研究生，主要研究方向为图像处理。
