基于實例的歸納式遷移學習研究
發(fā)布時間：2018-12-28 18:21
【摘要】：在全球信息化大潮的推動下,數(shù)據(jù)量日益增長,其增速讓人驚嘆,面對如此之多的信息和數(shù)據(jù)突如其來的沖擊大腦,人們沒有時間看這些數(shù)據(jù),人們的關注已經(jīng)轉到可貴的應付手段上。因此,人們必須找到有效方法,應對處理大量的信息以此來高效、準確的找到有價值的信息。首先,本文針對具有相關性的數(shù)據(jù),考慮數(shù)據(jù)之間具有層次關系,將與目標領域相關的數(shù)據(jù)根據(jù)相關性按不同比例調(diào)整權重,在經(jīng)典遷移學習算法Tr Ada Boost中引入層次相關性、權重調(diào)整策略、錯分樣本權重約束,從而提出一種結合層次相關性的遷移學習算法,以解決具有層次關系的數(shù)據(jù),高效調(diào)整權重的問題。在實驗部分,本文將基于層次相關性的遷移學習算法與SVM、Tr Adaboost算法的正確率、查準率、查全率進行對比,對實驗數(shù)據(jù)分析得到基于層次相關性的數(shù)據(jù)具有更準確的分類結果。針對目標領域與多個源領域都相近,但源領域與目標領域不一樣,多個源領域也都不一樣,都是一個大的源領域下面的多個小的源領域領域,這些小的源領域還有些相關性,從多個小的源領域往一個目標領域遷移。針對具有多個源領域,單個源領域樣本不足,負遷移的問題,提出一種多源實例遷移學習算法,考慮多個源領域的知識,使目標領域能綜合考慮運用每個源領域的知識,該方法先對源領域和目標領域做并集訓練出分類器,經(jīng)過測試后保留那些取并集后提升分類效果的源領域。然后,再將留下的源領域做并集,做Tr Adaboost遷移學習,測試后按照指定的規(guī)則選擇最終的集合作為源領域,與目標領域共同訓練出分類器。最后,通過實驗對第三章,第四章所提出的基于層次相關性的遷移學習和多源實例遷移學習進行詳細的描述,并將實驗結果做出客觀的分析總結,對比改進前后的正確率,查準率,查全率。證明了基于層次相關性的遷移學習算法和多源實例遷移學習算法能夠非常有效地提高分類器的分類效果。
[Abstract]:Driven by the tide of global information technology, the amount of data is growing day by day, and the growth rate is amazing. In the face of so much information and data suddenly coming to the brain, people do not have time to look at these data. Attention has shifted to valuable coping techniques. Therefore, people must find an effective way to deal with a large amount of information in order to find valuable information efficiently and accurately. First of all, considering the hierarchical relationship between the data, this paper adjusts the weight of the data related to the target domain according to the correlation according to different proportions, and introduces the hierarchical correlation into the classical migration learning algorithm Tr Ada Boost. In order to solve the problem of data with hierarchical relationship and adjust weights efficiently, a transfer learning algorithm combining hierarchical correlation is proposed. In the experiment part, we compare the transfer learning algorithm based on hierarchical correlation with the correct rate, precision rate and recall rate of SVM,Tr Adaboost algorithm, and get more accurate classification results by analyzing the experimental data. The target domain is similar to multiple source domains, but the source domain is not the same as the target domain, and many source domains are not the same, they are many small source fields under a large source domain, and these small source domains have some relevance. Migrate from multiple small source domains to one target domain. In order to solve the problem of multiple source domains with insufficient samples and negative migration, a multi-source instance transfer learning algorithm is proposed, in which the knowledge of multiple source domains is considered, so that the target domain can comprehensively consider the use of knowledge in each source domain. The method firstly combines the source domain and the target domain to train the classifier. After the test, the source domain that is used to improve the classification effect is reserved. Then, the source domain is merged and the Tr Adaboost migration learning is done. After testing, the final set is selected as the source domain according to the specified rules, and the classifier is trained together with the target domain. Finally, the transfer learning based on hierarchical correlation and multi-source instance transfer learning proposed in chapter 3 and chapter 4 are described in detail through experiments, and the experimental results are objectively analyzed and summarized, and the correct rate before and after the improvement is compared. Precision rate It is proved that the hierarchical correlation based migration learning algorithm and the multi-source instance migration learning algorithm can effectively improve the classification effect of the classifier.
【學位授予單位】：遼寧大學
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：TP181
本文編號：2394269
[Abstract]:Driven by the tide of global information technology, the amount of data is growing day by day, and the growth rate is amazing. In the face of so much information and data suddenly coming to the brain, people do not have time to look at these data. Attention has shifted to valuable coping techniques. Therefore, people must find an effective way to deal with a large amount of information in order to find valuable information efficiently and accurately. First of all, considering the hierarchical relationship between the data, this paper adjusts the weight of the data related to the target domain according to the correlation according to different proportions, and introduces the hierarchical correlation into the classical migration learning algorithm Tr Ada Boost. In order to solve the problem of data with hierarchical relationship and adjust weights efficiently, a transfer learning algorithm combining hierarchical correlation is proposed. In the experiment part, we compare the transfer learning algorithm based on hierarchical correlation with the correct rate, precision rate and recall rate of SVM,Tr Adaboost algorithm, and get more accurate classification results by analyzing the experimental data. The target domain is similar to multiple source domains, but the source domain is not the same as the target domain, and many source domains are not the same, they are many small source fields under a large source domain, and these small source domains have some relevance. Migrate from multiple small source domains to one target domain. In order to solve the problem of multiple source domains with insufficient samples and negative migration, a multi-source instance transfer learning algorithm is proposed, in which the knowledge of multiple source domains is considered, so that the target domain can comprehensively consider the use of knowledge in each source domain. The method firstly combines the source domain and the target domain to train the classifier. After the test, the source domain that is used to improve the classification effect is reserved. Then, the source domain is merged and the Tr Adaboost migration learning is done. After testing, the final set is selected as the source domain according to the specified rules, and the classifier is trained together with the target domain. Finally, the transfer learning based on hierarchical correlation and multi-source instance transfer learning proposed in chapter 3 and chapter 4 are described in detail through experiments, and the experimental results are objectively analyzed and summarized, and the correct rate before and after the improvement is compared. Precision rate It is proved that the hierarchical correlation based migration learning algorithm and the multi-source instance migration learning algorithm can effectively improve the classification effect of the classifier.
【學位授予單位】：遼寧大學
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：TP181
【參考文獻】
相關期刊論文 前10條
1 王勇;;云計算環(huán)境下信息保護與防泄露系統(tǒng)設計及實現(xiàn)[J];中國管理信息化;2017年01期
2 潘炯光;韋余永;;一種基于領域語義相關性挖掘的遷移學習方法[J];西南師范大學學報(自然科學版);2016年05期
3 張博;史忠植;趙曉非;張建華;;一種基于跨領域典型相關性分析的遷移學習方法[J];計算機學報;2015年07期
4 黃宜華;;大數(shù)據(jù)機器學習系統(tǒng)研究進展[J];大數(shù)據(jù);2015年01期
5 尹寶才;王文通;王立春;;深度學習研究綜述[J];北京工業(yè)大學學報;2015年01期
6 何清;李寧;羅文娟;史忠植;;大數(shù)據(jù)下的機器學習算法綜述[J];模式識別與人工智能;2014年04期
7 張倩;李海港;李明;程玉虎;;基于多源動態(tài)TrAdaBoost的實例遷移學習方法[J];中國礦業(yè)大學學報;2014年04期
8 吳肖炎;郭瑞;;基于機器學習的計算機安全技術綜述(上)[J];保密科學技術;2013年03期
9 ;大數(shù)據(jù)時代[J];中國電子科學研究院學報;2013年01期
10 賀英杰;葉宗民;金吉學;;機器學習在入侵檢測中的應用綜述[J];計算機安全;2010年03期
相關碩士學位論文 前6條
1 嚴海銳;多源遷移學習算法研究[D];華南理工大學;2016年
2 王欣;基于遷移學習的跨領域推薦的方法研究[D];杭州電子科技大學;2015年
3 韋余永;基于實例與特征的遷移學習文本分類方法研究[D];西南大學;2015年
4 郭世碩;多源遷移學習的研究[D];西安電子科技大學;2014年
5 沈鍵;電子商務的個性化協(xié)同過濾推薦算法研究[D];上海交通大學;2013年
6 戴文淵;基于實例和特征的遷移學習算法研究[D];上海交通大學;2009年
，本文編號：2394269
本文鏈接：http://www.sikaile.net/kejilunwen/zidonghuakongzhilunwen/2394269.html
最近更新
教材專著
