Visualization of Non-vectorial Data Using Twin Kernel Embedding

Author(s)
Guo, Y
Gao, J
Kwan, PH
Publication Date
2006
Abstract
Visualization of non-vectorial objects is not easy in practicedue to their lack of convenient vectorial representation.Representative approaches are Kernel PCA and KernelLaplacian Eigenmaps introduced recently in our research.Extending our earlier work, we propose in this papera new algorithm called Twin Kernel Embedding (TKE)that preserves the similarity structure of input data in the latentspace. Experimental evaluation on MNIST handwrittendigit database verifies that TKE outperforms related methods.
Citation
Proceedings of The 2006 International Workshop on Integrating AI and Data Mining (AIDM'06), p. 11-17
ISBN
0769527302
Link
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Title
Visualization of Non-vectorial Data Using Twin Kernel Embedding
Type of document
Conference Publication
Entity Type
Publication

Files:

NameSizeformatDescriptionLink