Table of contents
Detailed principle of support vector machine SVM
SVM definition
SVM theory
Detailed explanation of Libsvm toolbox
Introduction
Parameter description
Errors and common problems
Complete code and data download link:
remote sensing image classification and recognition based on SVM, remote sensing image classification and recognition based on support vector machine SVM ( Complete code, complete data)_SVM multi-classification problem resources in image matching-CSDN library https://download.csdn.net/download/abc991835105/88217968
SVM application examples, automatic recognition of reagent strip images based on support vector machine SVM
code
results Analysis
Outlook
Detailed principles of support vector machine SVM
Definition of SVM
Support vector machines (SVM) is a two-classification model. Its basic model is a linear classifier defined with the largest interval on the feature space. The largest interval makes it different from the perceptron; SVM also includes kernel techniques. , which makes it an essentially nonlinear classifier. The learning strategy of SVM is to maximize the interval, which can be formalized as a problem of solving convex quadratic programming, which is also equivalent to the minimization problem of the regularized hinge loss function. The learning algorithm of SVM is an optimization algorithm for solving convex quadratic programming.
(1) Support Vector Machine (SVM) is a generalized linear classifier that performs two classifications on data. Its classification boundary is the maximum interval hyperplane that solves the learning sample.
(2) SVM uses the hinge loss function to calculate the empirical risk and adds a regularization term to the solution system to optimize the structural risk. It is a classifier with sparseness and robustness.
(3) SVM can perform nonlinear classification by introducing kernel functions.