[模式识别RVMPRyc.pptVIP

Presentation ? 2012 BJTU BEIJING JIAOTONG UNIVERSITY 乳腺X线图像中微钙化点簇的检测 Detection of Clustered Micro-calcifications in Mammograms 姚畅 chyao@bjtu.edu.cn 北京交通大学 2012-3-17 Evaluation only. Created with Aspose.Slides for .NET 3.5 Client Profile 5.2.0.0. Copyright 2004-2011 Aspose Pty Ltd. 2 . 2 . 内容提要： 一、相关向量机(Relevance Vector Machine, RVM)理论 二、基于自适应核学习的乳腺微钙化点簇检测 Evaluation only. Created with Aspose.Slides for .NET 3.5 Client Profile 5.2.0.0. Copyright 2004-2011 Aspose Pty Ltd. 3 乳腺X线图像中微钙化点簇的检测 Detection of Clustered Microcalcifications in Mammograms . 3 . Relevance Vector Machine (RVM)： 与support vector machine (SVM) 的关系： -- 都是通过对训练样本集进行训练，获得训练好的模型，实现对新数据的预测。 SVM： -- The number of support vectors grows linearly with the size of the training set. -- Predictions are not probabilistic. -- Necessary to estimate the error/margin trade-off parameter C -- The kernel function K(x; xi ) must satisfy Mercer’s condition. That is, it must be the continuous symmetric kernel of a positive integral operator. Evaluation only. Created with Aspose.Slides for .NET 3.5 Client Profile 5.2.0.0. Copyright 2004-2011 Aspose Pty Ltd. 4 . 4 . Relevance Vector Machine (RVM)： 给定数据集{xi, ti} 从而，对于待预测数据x* Evaluation only. Created with Aspose.Slides for .NET 3.5 Client Profile 5.2.0.0. Copyright 2004-2011 Aspose Pty Ltd. Relevance Vector Machine (RVM)： 为避免过拟合（over-fitting），对w加上先决条件： 从而， 其中， 剩下的工作为求： Evaluation only. Created with Aspose.Slides for .NET 3.5 Client Profile 5.2.0.0. Copyright 2004-2011 Aspose Pty Ltd. Relevance Vector Machine (RVM)： Evaluation only. Created with Aspose.Slides for .NET 3.5 Client Profile 5.2.0.0. Copyright 2004-2011 Aspose Pty Ltd. ? Evaluation only. Created with Aspose.Slides for .NET 3.5 Client Profile 5.2.0.0. Copyright 2004-2011 Aspose Pty Ltd. (Marginal likelihood) taking logs, get log marginal likelihood: Evaluation only. Created with Aspose.Slides for .NET 3.5 Client Profile 5.2.0.0. Copyright 2004-2011 Aspose Pty Ltd. 获得 和 的更新值后,将其返回计算m和 ，直到满足收敛标准。 而 Evaluatio