Back
Joint Kernel Maps
We develop a methodology for solving high dimensional dependency estimation problems between pairs of data types, which is viable in the case where the output of interest has very high dimension, e.g., thousands of dimensions. This is achieved by mapping the objects into continuous or discrete spaces, using joint kernels. Known correlations between input and output can be defined by such kernels, some of which can maintain linearity in the outputs to provide simple (closed form) pre-images. We provide examples of such kernels and empirical results.
@inproceedings{3472, title = {Joint Kernel Maps}, journal = {Proceedings of the 8th International Work-Conference on Artificial Neural Networks (Computational Intelligence and Bioinspired System)}, booktitle = {Proceedings of the 8th InternationalWork-Conference on Artificial Neural Networks}, abstract = {We develop a methodology for solving high dimensional dependency estimation problems between pairs of data types, which is viable in the case where the output of interest has very high dimension, e.g., thousands of dimensions. This is achieved by mapping the objects into continuous or discrete spaces, using joint kernels. Known correlations between input and output can be defined by such kernels, some of which can maintain linearity in the outputs to provide simple (closed form) pre-images. We provide examples of such kernels and empirical results.}, volume = {LNCS 3512}, pages = {176-191}, editors = {J Cabestany and A Prieto and F Sandoval}, publisher = {Springer}, organization = {Max-Planck-Gesellschaft}, school = {Biologische Kybernetik}, address = {Berlin Heidelberg, Germany}, year = {2005}, slug = {3472}, author = {Weston, J. and Sch{\"o}lkopf, B. and Bousquet, O.} }