We present a new approach, called local discriminant embedding (LDE), to manifold learning and pattern classification. In our framework, the neighbor and class relations of data a...
This paper describes a local ensemble kernel learning technique to recognize/classify objects from a large number of diverse categories. Due to the possibly large intraclass featu...
We construct a class of envelope surfaces in Rd , more precisely envelopes of balls. An envelope surface is a closed C1 (tangent continuous) manifold wrapping tightly around the u...
Most existing semi-supervised learning methods are based on the smoothness assumption that data points in the same high density region should have the same label. This assumption, ...
The Gaussian process latent variable model (GP-LVM) is a generative approach to nonlinear low dimensional embedding, that provides a smooth probabilistic mapping from latent to da...