专利内容由知识产权出版社提供
专利名称：Density estimation and/or manifold learning发明人：Antonio Criminisi,Jamie Daniel Joseph
Shotton,Ender Konukoglu
申请号：US13528866申请日：20120621公开号：US054365B2公开日：20150210
专利附图：
摘要：Density estimation and/or manifold learning are described, for example, forcomputer vision, medical image analysis, text document clustering. In variousembodiments a density forest is trained using unlabeled data to estimate the data
distribution. In embodiments the density forest comprises a plurality of random decisiontrees each accumulating portions of the training data into clusters at their leaves. Inembodiments probability distributions representing the clusters at each tree are
aggregated to form a forest density which is an estimate of a probability density functionfrom which the unlabeled data may be generated. A mapping engine may use theclusters at the leaves of the density forest to estimate a mapping function which mapsthe unlabeled data to a lower dimensional space whilst preserving relative distances orother relationships between the unlabeled data points. A sampling engine may use thedensity forest to randomly sample data from the forest density.
申请人：Antonio Criminisi,Jamie Daniel Joseph Shotton,Ender Konukoglu
地址：Cambridge GB,Cambridge GB,Cambridge GB
国籍：GB,GB,GB
代理机构：Zete Law, P.L.L.C.
代理人：Miia Sula,Micky Minhas
更多信息请下载全文后查看
