Wright CS 707 - Support Vector Machines (64 pages)

Previewing pages 1, 2, 3, 4, 30, 31, 32, 33, 34, 61, 62, 63, 64 of 64 page document View the full content.
View Full Document

Support Vector Machines



Previewing pages 1, 2, 3, 4, 30, 31, 32, 33, 34, 61, 62, 63, 64 of actual document.

View the full content.
View Full Document
View Full Document

Support Vector Machines

24 views


Pages:
64
School:
Wright State University
Course:
Cs 707 - Information Retrieval

Unformatted text preview:

Support Vector Machines Adapted from Lectures by Raymond Mooney UT Austin and Andrew Moore CMU Prasad L15SVM 1 Text classification Earlier Algorithms for text classification K Nearest Neighbor classification Vector space classification using centroids and hyperplanes that split them Simple expensive at test time low bias high variance non linear Simple linear classifier perhaps too simple high bias low variance Today Prasad SVMs Some empirical evaluation and comparison Text specific issues in classification L15SVM 2 Linear classifiers Which Hyperplane Lots of possible solutions for a b c Some methods find a separating hyperplane but not the optimal one according to some criterion of expected goodness Support Vector Machine SVM finds an optimal solution Prasad This line represents the decision boundary ax by c 0 Maximizes the distance between the hyperplane and the difficult points close to decision boundary Intuition Then there are fewer uncertain classification decisions L15SVM 3 15 0 Another intuition If we place a fat separator between classes we have less choices and so the capacity of the model has been decreased Define the margin of a linear classifier as the width that the boundary could be increased by before hitting a datapoint Prasad 4 Decision hyperplane Recall that a decision hyperplane can be defined by the intercept term b the normal vector w weight vector which is perpendicular to the hyperplane All points x on the hyperplane satisfy Prasad L15SVM 5 Support Vector Machine SVM SVMs maximize the margin around the separating hyperplane A k a large margin classifiers The decision function is fully specified by a subset of training samples the support vectors Solving SVMs is a Quadratic programming problem Seen by many as most successful current text classification method Prasad Support vectors L15SVM Maximize margin 6 15 1 Robustness of SVMs If we make a small error in the location of the boundary this approach minimizes misclassification Recall that



View Full Document

Access the best Study Guides, Lecture Notes and Practice Exams

Loading Unlocking...
Login

Join to view Support Vector Machines and access 3M+ class-specific study document.

or
We will never post anything without your permission.
Don't have an account?
Sign Up

Join to view Support Vector Machines and access 3M+ class-specific study document.

or

By creating an account you agree to our Privacy Policy and Terms Of Use

Already a member?