FAFU机器学习08-1 Support Vector Machine课件.pptxVIP

Foundations of Machine LearningSupport Vector Machine （支持向量机） Top 10 algorithms in data miningC4.5K-MeansSVMAprioriEM (Maximum Likelihood)PageRankAdaBoostKNNNa?veBayesCART Support Vector Machine背景间隔与支持向量对偶问题核函数软间隔与正则化支持向量回归SVM in sklearn2023/11/4Support Vector MachineLesson 7 - 3 BackgroundThe original SVM algorithm was invented by?Vladimir N. Vapnik?and?Alexey Ya. Chervonenkis?in 1963Maximal Margin ClassifierIn 1992,?Bernhard E. Boser,?Isabelle M. Guyon and Vladimir N. Vapnik suggested a way to create nonlinear classifiers by applying the?kernel trick?to maximum-margin hyperplanes.The kernelized version using the Kernel TrickThe current standard incarnation (soft margin) was proposed by?Corinna Cortes?and Vapnik in 1993 and published in 1995.Soft Margin ClassifierThe soft-margin kernelized version (which combine 1, 2 and 3)2023/11/4Support Vector MachineLesson 7 - 4 BackgroundIn 1996, Vapnik et al. proposed a version of SVM to perform regression instead of classification.?Support Vector Regression (SVR)In?machine learning,?support vector machines?(SVMs, also?support vector networks) are?supervised learning ?models with associated learning?algorithms?that analyze data used for?classification?and?regression analysis. However,??it is mostly used?in?classification problems.SVM becomes popular because of its success in handwritten digit recognition 2023/11/4Support Vector MachineLesson 7 - 5 ProsKernel-based framework is very powerful, flexibleWork very well in practice, even with very small training sample sizesSolution can be formulated as a quadratic programmingMany publicly available SVM packages: e.g. LIBSVM, LIBLINEAR, SVMLight ConsCan be tricky to select best kernel function for a problemComputation, memory At training time, must compute kernel values for all example pairs Learning can take a very long time for large-scale problems2023/11/4Support Vector MachineLesson 7 - 6 Support Vector Machine背景间隔与支持向量对偶问题核函数软间隔与正则化支持向量回归SVM in sklearn2023/11/4Support Ve