信息与控制
信息與控製
신식여공제
INFORMATION AND CONTROL
2015年
2期
159-164
,共6页
鲁淑霞%焦彩红%周扬帆%佟乐
魯淑霞%焦綵紅%週颺帆%佟樂
로숙하%초채홍%주양범%동악
最大向量夹角间隔分类器%最小包围球%正则化%核向量机
最大嚮量夾角間隔分類器%最小包圍毬%正則化%覈嚮量機
최대향량협각간격분류기%최소포위구%정칙화%핵향량궤
maximum vector-angular margin classifier%minimum enclosing ball%regularized%core vector machine
针对大数据集如何有效地进行训练的问题,基于最大向量夹角间隔分类器(maximum vector-angular margin classifier,MAMC),提出了求解最优向量d的不同方法来得到中心向量夹角间隔分类器(central vector-angular margin classifier, CAMC),进而证明了 CAMC 等价于最小包围球问题(minimum enclosed ball, MEB)。但是鉴于 MEB 对参数的敏感性,又提出了正则化核向量机(regularized core vector machine,RCVM),将CAMC与RCVM结合得到中心向量夹角间隔正则化核向量机(regularized core vector machine with central vector-angular margin,CAM-CVM)。基于基准数据集的实验表明,CAMC具有更好的分类性能且CAMCVM可以有效快速地训练大规模数据集。
針對大數據集如何有效地進行訓練的問題,基于最大嚮量夾角間隔分類器(maximum vector-angular margin classifier,MAMC),提齣瞭求解最優嚮量d的不同方法來得到中心嚮量夾角間隔分類器(central vector-angular margin classifier, CAMC),進而證明瞭 CAMC 等價于最小包圍毬問題(minimum enclosed ball, MEB)。但是鑒于 MEB 對參數的敏感性,又提齣瞭正則化覈嚮量機(regularized core vector machine,RCVM),將CAMC與RCVM結閤得到中心嚮量夾角間隔正則化覈嚮量機(regularized core vector machine with central vector-angular margin,CAM-CVM)。基于基準數據集的實驗錶明,CAMC具有更好的分類性能且CAMCVM可以有效快速地訓練大規模數據集。
침대대수거집여하유효지진행훈련적문제,기우최대향량협각간격분류기(maximum vector-angular margin classifier,MAMC),제출료구해최우향량d적불동방법래득도중심향량협각간격분류기(central vector-angular margin classifier, CAMC),진이증명료 CAMC 등개우최소포위구문제(minimum enclosed ball, MEB)。단시감우 MEB 대삼수적민감성,우제출료정칙화핵향량궤(regularized core vector machine,RCVM),장CAMC여RCVM결합득도중심향량협각간격정칙화핵향량궤(regularized core vector machine with central vector-angular margin,CAM-CVM)。기우기준수거집적실험표명,CAMC구유경호적분류성능차CAMCVM가이유효쾌속지훈련대규모수거집。
For effective training on large datasets,we propose an alternate method to find the optimal vector,d, using the central vector-angular margin classifier (CAMC),which is based on the maximum vector-angular margin classifier.The CAMC can be considered to be equivalent to the corresponding minimum enclosing ball (MEB)problem.However,we have found that the MEB is very sensitive to the selection of the trade-off pa-rameter,so we propose using a regularized core vector machine (RCVM).By connecting the CAMC to the RCVM,we obtain a central vector-angular margin regularized core vector machine (CAMCVM).Experimen-tal results from the UCI datasets show that the CAMC has a better generalized performance,while the CAM-CVM can be used for effective training on large datasets.