国产bbaaaaa片,成年美女黄网站色视频免费,成年黄大片,а天堂中文最新一区二区三区,成人精品视频一区二区三区尤物

首頁(yè)> 外文學(xué)位 >Collaborative filtering using machine learning and statistical techniques.
【24h】

Collaborative filtering using machine learning and statistical techniques.

機(jī)譯：使用機(jī)器學(xué)習(xí)和統(tǒng)計(jì)技術(shù)進(jìn)行協(xié)作過(guò)濾。

獲取原文
獲取原文并翻譯 | 示例
  • 摘要
  • 著錄項(xiàng)
  • 相似文獻(xiàn)
  • 相關(guān)主題

摘要

Collaborative filtering (CF), a very successful recommender system, is one of the applications of data mining for incomplete data. The main objective of CF is to make accurate recommendations from highly sparse user rating data.;My contributions to this research topic include proposing the frameworks of imputation-boosted collaborative filtering (IBCF) and imputed neighborhood based collaborative filtering (INCF). We also proposed a model-based CF technique, TAN-ELR CF, and two hybrid CF algorithms, sequential mixture CF and joint mixture CF. Empirical results show that our proposed CF algorithms have very good predictive performances.;In the investigation of applying imputation techniques in mining incomplete data, we proposed imputation-helped classifiers, and VCI predictors (voting on classifications from imputed learning sets), both of which resulted in significant improvement in classification performance for incomplete data over conventional machine learned classifiers, including kNN, neural network, one rule, decision table, SVM, logistic regression, decision tree (C4.5), random forest, and decision list (PART), and the well-known Bagging predictors. The main imputation techniques involved in these algorithms include EM (expectation maximization) and BMI (Bayesian multiple imputation).
機(jī)譯：協(xié)作過(guò)濾（CF）是一種非常成功的推薦系統(tǒng)，是不完整數(shù)據(jù)的數(shù)據(jù)挖掘應(yīng)用之一。 CF的主要目的是從高度稀疏的用戶評(píng)分?jǐn)?shù)據(jù)中提出準(zhǔn)確的建議。我對(duì)這一研究主題的貢獻(xiàn)包括提出了歸因增強(qiáng)協(xié)作過(guò)濾（IBCF）和歸因鄰域協(xié)作過(guò)濾（INCF）框架。我們還提出了基于模型的CF技術(shù)TAN-ELR CF，以及兩種混合CF算法：順序混合CF和聯(lián)合混合CF。實(shí)證結(jié)果表明，我們提出的CF算法具有很好的預(yù)測(cè)性能。在將插補(bǔ)技術(shù)應(yīng)用于不完整數(shù)據(jù)挖掘的研究中，我們提出了插補(bǔ)幫助的分類器和VCI預(yù)測(cè)器（對(duì)插補(bǔ)學(xué)習(xí)集的分類進(jìn)行投票）。與傳統(tǒng)的機(jī)器學(xué)習(xí)分類器（包括kNN，神經(jīng)網(wǎng)絡(luò)，一條規(guī)則，決策表，SVM，邏輯回歸，決策樹(shù)（C4.5），隨機(jī)森林和決策列表（PART））相比，不完整數(shù)據(jù)的分類性能得到了顯著改善，以及著名的Bagging預(yù)測(cè)變量。這些算法中涉及的主要插補(bǔ)技術(shù)包括EM（期望最大化）和BMI（貝葉斯多重插補(bǔ)）。

著錄項(xiàng)

相似文獻(xiàn)

  • 外文文獻(xiàn)
  • 中文文獻(xiàn)
  • 專利
獲取原文

客服郵箱：kefu@zhangqiaokeyan.com

京公網(wǎng)安備：11010802029741號(hào) ICP備案號(hào)：京ICP備15016152號(hào)-6 六維聯(lián)合信息科技 (北京) 有限公司?版權(quán)所有

  • 客服微信

  • 服務(wù)號(hào)