發(fā)布時間：2018-03-25 04:10

  本文選題：深度學(xué)習(xí)　切入點：遷移學(xué)習(xí)　出處：《系統(tǒng)工程與電子技術(shù)》2017年12期

【摘要】：針對武器裝備體系效能評估在高維噪聲小樣本數(shù)據(jù)條件下準(zhǔn)確性不高的問題,提出一種基于堆棧降噪自編碼與支持向量回歸機的混合模型。利用堆棧自編碼神經(jīng)網(wǎng)絡(luò)對通用深層特征的自主抽取能力,通過在相似源域大數(shù)據(jù)上預(yù)訓(xùn)練混合模型,獲得兩任務(wù)間的共有特征知識,借助對該知識的遷移,在目標(biāo)域微調(diào)該混合模型,從而提升支持向量回歸機在小樣本噪聲數(shù)據(jù)上的學(xué)習(xí)預(yù)測精度。在一定作戰(zhàn)想定背景下,結(jié)合武器裝備體系仿真試驗數(shù)據(jù),對該混合模型進行驗證。實驗結(jié)果表明,與傳統(tǒng)支持向量回歸機等模型相比,所提模型能夠更準(zhǔn)確地評估裝備效能。
[Abstract]:Aiming at the problem that the accuracy of weapon system effectiveness evaluation is not high under the condition of high dimension noise and small sample data, This paper presents a hybrid model based on stack denoising self-coding and support vector regression machine. By using the self-coding neural network of stack self-coding to extract general deep features, the hybrid model is pretrained on big data in the similar source domain. The common feature knowledge between the two tasks is obtained, and the hybrid model is fine-tuned in the target domain with the help of the migration of the knowledge, so as to improve the learning and prediction accuracy of the support vector regression machine on the small sample noise data. Combined with the simulation data of weapon equipment system, the hybrid model is verified. The experimental results show that compared with the traditional support vector regression model, the proposed model can evaluate the equipment effectiveness more accurately.
【作者單位】： 國防大學(xué)信息作戰(zhàn)與指揮訓(xùn)練教研部;航天飛行器生存技術(shù)與效能評估實驗室;
【基金】：國家自然科學(xué)基金(61403401) 軍民共用重大研究計劃聯(lián)合基金項目(U1435218)資助課題
【分類號】：E92;TP181

【相似文獻】

相關(guān)期刊論文 前3條

1 劉輝;楊俊安;許學(xué)忠;;隱馬爾可夫模型和支持向量機混合模型聲識別[J];探測與控制學(xué)報;2009年06期

2 馬維嶸,陶其恒,榮光;子彈氣囊拋射的一維與零維混合模型[J];彈道學(xué)報;2003年03期

3 單洪春;;基于空間特性的彈道特征抽取[J];飛行器測控學(xué)報;2012年02期

，

本文編號：1661470