Dimensionality reduction involves mapping a set of high dimensional input points onto a low dimensional manifold so that "similar" points in input space are mapped to ne...
Several recently-proposed architectures for highperformance
object recognition are composed of two main
stages: a feature extraction stage that extracts locallyinvariant
feature...
Koray Kavukcuoglu, Marc'Aurelio Ranzato, Rob Fergu...
This paper describes a method for recognizing partially occluded objects under different levels of illumination brightness by using the eigenspace analysis. In our previous work, w...
A key challenge in applying kernel-based methods for discriminative learning is to identify a suitable kernel given a problem domain. Many methods instead transform the input data...
Abstract. The eigenspectrum of a graph Laplacian encodes smoothness information over the graph. A natural approach to learning involves transforming the spectrum of a graph Laplaci...