Escaping the Convex Hull with Extrapolated Vector Machines
نویسنده
چکیده
Maximum margin classifiers such as Support Vector Machines (SVMs) critically depends upon the convex hulls of the training samples of each class, as they implicitly search for the minimum distance between the convex hulls . We propose Extrapolated Vector Machines (XVMs) which rely on extrapolations outside these convex hulls. XVMs improve SVM generalization very significantly on the MNIST [7] OCR data. They share similarities with the Fisher discriminant: maximize the inter-class margin while minimizing the intra-class disparity.
منابع مشابه
Escaping the Convex Hull with Extrapolated Vector Machines
Extrapolated Vector Machines. Patrick Ha ner AT&T Labs-Research, 200 Laurel Ave, Middletown, NJ 07748 [email protected] Abstract Maximum margin classi ers such as Support Vector Machines (SVMs) critically depends upon the convex hulls of the training samples of each class, as they implicitly search for the minimum distance between the convex hulls. We propose Extrapolated Vector Machines...
متن کاملEffects of Soft Margins on Learning Curves of Support Vector Machines
The generalization properties of support vector machines (SVMs) are examined. From a geometrical point of view, the estimated parameter of an SVM is the one nearest the origin in the convex hull formed with given examples. Since introducing soft margins is equivalent to reducing the convex hull of the examples, an SVM with soft margins has a different learning curve from the original. In this p...
متن کاملAn asymptotic statistical analysis of support vector machines with soft margins
The generalization properties of support vector machines (SVMs) are examined. From a geometrical point of view, the estimated parameter of an SVM is the one nearest the origin in the convex hull formed with given examples. Since introducing soft margins is equivalent to reducing the convex hull of the examples, an SVM with soft margins has a different learning curve from the original. In this p...
متن کاملA Generic Nearest Point Algorithm for Solving Support Vector Machines
We propose a nearest point algorithm (NPA) for optimization of a family of Support Vector Machines (SVM) methods. Geometrically, optimizing SVM corresponds to finding the nearest points between two polyhedrons. In classification, the hard margin case corresponds to finding the closest points of the convex hull of each class. The soft margin case corresponds to finding the closest points in the ...
متن کاملFace Replacement with HOG and SVM
This project is an attempt to completely replace faces in video frames using Support Vector Machines (SVM) as classifiers on Histogram of Oriented Gradients (HOG). We trained an SVM classifier to first identify a face in an image using HOG descriptors and then identify fiducial markers like eyes, nose and mouth in the identified face using Matlab’s Cascade Object Descriptor. Once a convex hull ...
متن کامل