查詢結果分析
來源資料
相關文獻
- A Review of Reduced Kernel Trick in Machine Learning
- 具自適應核形狀參數的徑向基底函數網路
- 核機率密度函數折線圖之研究
- 均勻分配轉換和最小平方法在密度函數估計
- 改善多層次人工神經網路學習速度之探討
- 改良式核迴歸函數折線圖之研究
- An On-Line Learning Neural Network for Radar Signal Classification
- 非監督類神經網路之迭代合併式學習法則
- 估計機率函數及其各階微分的最小最大風險
- 量大就是好?--評《大數據》[麥爾荀伯格(Viktor Mayer-Schonberger)、庫基耶(Kenneth Cukier)著;林俊宏譯,《大數據》(Big Data: A Revolution That Will Transform How We Live, Work and Think)(天下文化,2013)]
頁籤選單縮合
題名 | A Review of Reduced Kernel Trick in Machine Learning=縮減核函數在機器學習的應用與回顧 |
---|---|
作者姓名(中文) | 葉倚任; 陳素雲; 鮑興國; 李育杰; | 書刊名 | 中國統計學報 |
卷期 | 52:1 2014.03[民103.03] |
頁次 | 頁85-114 |
分類號 | 312.13 |
關鍵詞 | 巨量資料; 維度縮減; 核函數; 縮減核技巧; 監督式學習; 支撐向量法; Big data; Dimension reduction; Kernel methods; Reduced kernel trick; Supervised learning; Support vector machine; |
語文 | 英文(English) |
中文摘要 | 在此篇文章中我們將介紹縮減支撐向量機 (reduced support vector machine)的數學模型,其中包含在統計上的理論基礎、延伸版本以及在機器學習演算法上的應用。主要的內容首先將包含三種不同縮減資料集 (reduced set)的篩選方法 ,在實驗上我們也驗證透過這三種方法所得到較精簡的縮減集亦可以達到非常良好之效果。除了縮減資料集的篩選方法之外 ,我們也將介紹應用縮減支撐向量機之概念於機器學習演算法的例子,其中包含迴歸問題 (regression)與資料維度縮減問題 (dimension reduction)。最後 ,由於所遭遇的問題資料量日趨龐大,如何利用非線性模型處理如此龐大之資料也是目前許多研究所關心的議題。因此,我們也將介紹縮減支撐向量機於巨量資料的應用 ,其中包含利用縮減支撐向量機之概念於 MapReduce的架構之中,進而可以處理巨量資料之問題。 |
英文摘要 | We give a comprehensive introduction to the reduced support vector machine, its extensions and applications. We describe original RSVM algorithm and the statistical theory behind it. Three schemes for selecting the representative reduced set are introduced. These schemes lead to a smaller reduced set than the random sampling scheme without sacrificing prediction accuracy. Although smaller reduced set will have faster support vector machine training, one has to pay extra CPU time in learning the reduced set selection. In addition to classification, applications of reduced kernel trick to regression and dimension reduction are also included in this survey paper. We finally embed the RSVMs in the MapReduce framework for extremely large scale datasets. Some preliminary numerical studies show that RSVMs in MapReduce framework has a good potential for solving large scale nonlinear support vector machines. We believe that the reduced kernel trick will be an important technique in the Big Data era. |
本系統之摘要資訊系依該期刊論文摘要之資訊為主。