Published November 7, 2012
| Published
Journal Article
Open
Locally Learning Biomedical Data Using Diffusion Frames
- Creators
- Ehler, M.
- Filbir, F.
- Mhaskar, H. N.
Abstract
Diffusion geometry techniques are useful to classify patterns and visualize high-dimensional datasets. Building upon ideas from diffusion geometry, we outline our mathematical foundations for learning a function on high-dimension biomedical data in a local fashion from training data. Our approach is based on a localized summation kernel, and we verify the computational performance by means of exact approximation rates. After these theoretical results, we apply our scheme to learn early disease stages in standard and new biomedical datasets.
Additional Information
© 2012 Mary Ann Liebert, Inc. Published in Volume: 19 Issue 11: November 7, 2012 Online Ahead of Print: October 26, 2012. M.E. was supported by the NIH/DFG Research Career Transition Awards Program (EH 405/1-1/575910). The research of F.F. was partially funded by Deutsche Forschungsgemeinschaft grant FI 883/3-1. H.N.M. was supported, in part, by grant DMS-0908037 from the National Science Foundation and grant W911NF-09-1-0465 from the U.S. Army Research Office.Attached Files
Published - cmb.2012.0187.pdf
Files
cmb.2012.0187.pdf
Files
(536.0 kB)
Name | Size | Download all |
---|---|---|
md5:bc433cad018f28cd32e98eafed6e230f
|
536.0 kB | Preview Download |
Additional details
- Eprint ID
- 35856
- Resolver ID
- CaltechAUTHORS:20121206-130135849
- EH 405/1-1/ 575910
- NIH/DFG Research Career Transition Awards Program
- FI 883/3-1
- Deutsche Forschungsgemeinschaft (DFG)
- DMS-0908037
- NSF
- W911NF-09-1-0465
- Army Research Office (ARO)
- Created
-
2012-12-07Created from EPrint's datestamp field
- Updated
-
2021-11-09Created from EPrint's last_modified field