摘要
由于深度信念网络(DBN)结构难以确定,提出运用狼群算法确定DBN每层神经元个数,K-means聚类准确性确定是否增加隐含层的方法确定DBN结构.根据狼群算法以最小化所有样本重构误差的平方和为目标函数来确定DBN每层神经元的个数,以确定DBN的初步结构.为了检验DBN结构的有效性,利用DBN提取的数据特征进行聚类测试,进一步根据聚类结果来修正DBN,以获取DBN的最佳结构.实验中选取Iris数据集进行聚类测试,其结果表明,通过所提出的方法获取的DBN有效结构来处理原始数据,能够提高聚类的准确性.
It＇s difficult to determine the structure of deep belief network （DBN）, so raise the method that use the wolves algorithm to determine the number of DBN per layer of neurons, and K--means Clustering Accuracy Determines whether or not to increase the hidden layer method. According to the minimal reconstruction error function of wolves algorithm, it can work out the quantity of each neuron, so as to determine the initial structure of the DBN. In order to verify the effectiveness of the DBN structure, using DBN to extract the data characteristics of the clustering test, so can get the final structure of the DBN. The Iris dataset was tested in the experiment, the results show that the proposed method handles the raw data by the effective structure of the DBN obtained and improve the accuracy of clustering.
作者
周贤泉
宋威
ZHOU Xian-quan;SONG Wei(School of Internet of Things Engineering, Jiangnan University, Wuxi 214122, China)
出处
《微电子学与计算机》
CSCD
北大核心
2018年第7期28-34,共7页
Microelectronics & Computer
基金
国家自然科学基金(61673193)
中央高校基本科研业务费专项资金(JUSRP51635B
JUSRP51510)
江苏省自然科学基金(BK20150159)
关键词
深度信念网络
狼群算法
重构误差
聚类测试
deep belief networks
wolves algorithm
reconstruction error
clustering test
