Learning to Find Pre-Images
Abstract
We consider the problem of reconstructing patterns from a feature map. Learning algorithms using kernels to operate in a reproducing kernel Hilbert space (RKHS) express their solutions in terms of input points mapped into the RKHS. We introduce a technique based on kernel princi- pal component analysis and regression to reconstruct corresponding pat- terns in the input space (aka pre-images) and review its performance in several applications requiring the construction of pre-images. The intro- duced technique avoids difficult and/or unstable numerical optimization, is easy to implement and, unlike previous methods, permits the compu- tation of pre-images in discrete input spaces.
Cite
Text
Weston et al. "Learning to Find Pre-Images." Neural Information Processing Systems, 2003.Markdown
[Weston et al. "Learning to Find Pre-Images." Neural Information Processing Systems, 2003.](https://mlanthology.org/neurips/2003/weston2003neurips-learning/)BibTeX
@inproceedings{weston2003neurips-learning,
title = {{Learning to Find Pre-Images}},
author = {Weston, Jason and Schölkopf, Bernhard and Bakir, Gökhan H.},
booktitle = {Neural Information Processing Systems},
year = {2003},
pages = {449-456},
url = {https://mlanthology.org/neurips/2003/weston2003neurips-learning/}
}