![]() SVM has been shown to perform well in many real learning problems with a variety of settings and is often considered one of the best “out-of-the-box” classifiers. Since the separating hyperplane is supported (defined) by the vectors (data points) nearest the margin, so the algorithm is called SVM. SVM only uses the objects (samples) on the edges of the margin (called support vectors) to separate objects (samples) rather than using the differences in class means. 646 So the hyperplane is known as the maximum margin hyperplane. The goal of the SVM algorithm is to use a training set of objects (samples) separated into classes to find a hyperplane in the data space that produces the largest minimum distance (called margin) between the objects (samples) that belong to different classes. The basic model of SVMs was described in 1995 by Cortes and Vapnik. SVM 646 is a supervised machine learning algorithm that can be used for both classification and regression. Yinglin Xia, in Progress in Molecular Biology and Translational Science, 2020 7.4.2 Support vector machines (SVMs) One should always remember that although SVMs are very good approaches in resolving the issues raised by having a limited number of data for training, they might be a time-consuming approach if applied to a huge database. To select the parameters of SVMs, though, it seems that the cross-validation approach would be the best choice based on the studies carried out so far. By providing examples from different applications of SVMs, it was concluded that the RBF (Gaussian) kernel function is perhaps the best kernel to have an efficient SVM. Few issues were raised including selection of kernel functions and other parameters of SVMs. In this chapter, attempts were made to indicate how an SVM works and how it can be structured to provide reliable results. Support Vector Machines (SVMs) have been one of the most successful machine learning techniques in recent years, applied successfully to many engineering related applications including those of the petroleum and mining. Raoof Gholami, Nikoo Fakhari, in Handbook of Neural Computation, 2017 27.8 Summary ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |