本文選題：深度信念網(wǎng)絡(luò)　切入點：等效模型　出處：《電測與儀表》2017年23期 　論文類型：期刊論文

【摘要】：針對深度信念網(wǎng)絡(luò)(DBN)中小樣本情況下,訓(xùn)練模型泛化性較差,分類識別率不夠理想,系統(tǒng)性能有待提高等問題,研究了DBN的等效模型,分析了小樣本情況下識別率差的問題;并提出一種區(qū)間化權(quán)值擴展方法,擴大了樣本和權(quán)值的匹配空間,使判決更有利于正確分類,提高了小樣本情況下的圖像分類準(zhǔn)確性;用檢測與估值理論給出了算法能提高系統(tǒng)檢測性能的依據(jù),并在不同的數(shù)據(jù)庫上進(jìn)行了實驗測試,進(jìn)一步證明了小樣本情況下圖像分類準(zhǔn)確率的提高。最后,將該方法應(yīng)用到了小樣本絕緣子故障識別中。
[Abstract]:In view of the problems of poor generalization of training model, poor classification recognition rate, and system performance to be improved, the equivalent model of DBN is studied, and the problem of poor recognition rate under small sample is analyzed. An interval weight extension method is proposed, which expands the matching space between samples and weights, makes the decision more favorable to the correct classification, and improves the accuracy of image classification in the case of small samples. Based on the theory of detection and estimation, the basis of the algorithm to improve the detection performance of the system is given, and the experimental results are carried out on different databases, which further prove the improvement of the accuracy of image classification in the case of small samples. The method is applied to fault identification of small sample insulators.
【作者單位】： 華北電力大學(xué)電氣與電子工程學(xué)院;
【分類號】：TP181;TP391.41

【相似文獻(xiàn)】

相關(guān)期刊論文 前2條

1 崔璽;沈鉞;;電路等效模型的進(jìn)化建模研究[J];微計算機信息;2009年02期

2 馬迅;王賀;那景新;;車身概念設(shè)計階段CAE分析的肋筋等效模型[J];吉林大學(xué)學(xué)報(工學(xué)版);2009年06期

，

本文編號：1579108