Quasar photometric redshifts from incomplete data using deep learning

Image Reconstruction from Incomplete Data

Estimating Photometric Redshifts Using Genetic Algorithms

Photometry is used as a cheap and easy way to estimate redshifts of galaxies, which would otherwise require considerable amounts of expensive telescope time. However, the analysis of photometric redshift datasets is a task where it is sometimes difficult to achieve a high classification accuracy. This work presents a custom Genetic Algorithm (GA) for mining the Hubble Deep Field North (HDF-N) d...

Estimating Photometric Redshifts Using Support Vector Machines

We present a new approach to obtaining photometric redshifts using a kernel learning technique called Support Vector Machines (SVMs). Unlike traditional spectral energy distribution fitting, this technique requires a large and representative training set. When one is available, however, it is likely to produce results that are comparable to the best obtained using template fitting and artificia...

Photometric Redshifts of Galaxies in the Hubble Deep Field

We describe our application of broad-band photometric redshift techniques to faint galaxies in the Hubble Deep Field. To magnitudes AB(8140) < 26, the accuracy of the photometric redshifts is a few tenths and the reliability of the photometric redshifts approaches 100%. At fainter magnitudes the effects of photometric error on the photometric redshifts can be rigorously quantified and accounted...

Deep Learning-Guided Image Reconstruction from Incomplete Data

An approach to incorporate deep learning within an iterative image reconstruction framework to reconstruct images from severely incomplete measurement data is presented. Specifically, we utilize a convolutional neural network (CNN) as a quasi-projection operator within a least squares minimization procedure. The CNN is trained to encode high level information about the class of images being ima...