BSVMhttp://mloss.orgUpdates and additions to BSVMenWed, 30 Jan 2008 10:27:13 -0000BSVM 2.06<html><p> BSVM solves support vector machines (SVM) for the solution of large classification and regression problems. It includes three methods </p> <pre><code>* One vs. One multi-class classification using a bound-constrained formulation * Multi-class classification by solving a single optimization problem (again, a bounded formulation). * Multi-class classification using Crammer and Singer's formulation. * Regression using a bound-constrained formulation </code></pre><p>It also has an efficient implementation for linear SVMs. </p> <p>The current implementation borrows the structure of libsvm. Similar options are also adopted. For the bound-constrained formulation for classification and regression, BSVM uses a decomposition method. BSVM uses a simple working set selection which leads to faster convergences for difficult cases. The use of a special implementation of the opmization solver TRON allows BSVM to stably identify bounded variables. </p></html> ChihWei Hsu, ChihJen LinWed, 30 Jan 2008 10:27:13 -0000 vector machineskernel methodsmulti classlinear svmlarge scale learning