Title:
Using the latest Machine Learning techniques for non-linear regression
and newly developed matrix inversion methods to calculate Photometric
Redshifts in the Sloan Digital Sky Survey

Abstract:

I will quickly introduce galaxy photometric redshifts to this diverse
audience.  I will then discuss our program of calculating these redshifts
using non-linear regression techiques from the Machine Learning Community
and newly developed methods for inverting large non-sparse matrices that
have made this technique very competitive.

Collaborators:
Ashok Srivastava (NASA/Ames, Intelligent System Division)
Les Foster and students (San Jose State University, Department of Mathematics)
Paul Gazis (NASA/Ames, Kepler Mission)
Jeffrey Scargle (NASA/Ames, Space Sciences Division)