发明名称 |
CLASSIFICATION OF HIGH DIMENSIONAL DATA |
摘要 |
A method for classification of high dimensional data on graphs based on the Ginzburg-Landau functional. The method applies L2 gradient flow minimization of the Ginzburg-Landau diffuse interface energy functional to the case of functions defined on graphs. The method performs binary segmentations in a semi-supervised learning (SSL) framework and multiclass tasks are solved by recursively applying a sequence of binary segmentations. Examples illustrate the versatility of the methods on a variety of datasets including congressional voting records, high dimensional test data, and machine learning in image processing. |
申请公布号 |
US2014204092(A1) |
申请公布日期 |
2014.07.24 |
申请号 |
US201313859721 |
申请日期 |
2013.04.09 |
申请人 |
CALIFORNIA THE REGENTS OF THE UNIVERSITY OF |
发明人 |
Bertozzi Andrea;Flenner Arjuna |
分类号 |
G06T11/20 |
主分类号 |
G06T11/20 |
代理机构 |
|
代理人 |
|
主权项 |
1. A method for classifying high dimensional data comprising:
(a) specifying an initial set of features within a data set of high dimensional data; (b) determining edge weights with a similarity function w(x,y); (c) building a graph based on the determined edge weights; (d) minimizing a Ginzburg-Landau energy functional with one or more constraints or fidelity terms; and (e) segmenting data into two classes. |
地址 |
US |