Filter and export

Publications

What is a Publication?
42 Publications visible to you, out of a total of 42
Automatic Galaxy Classification via Machine Learning Techniques: Parallelized Rotation/Flipping INvariant Kohonen Maps (PINK)

Abstract

Not specified

Authors: K. L. Polsterer, F. Gieseke, C. Igel

Date Published: 1st Sep 2015

Publication Type: InProceedings

Analyzing Complex and Structured Data via Unsupervised Learning Techniques

Abstract

Not specified

Authors: K. L. Polsterer, F. Gieseke, N. Gianniotis, S. D. Kuegler

Date Published: 1st Aug 2015

Publication Type: Journal

Featureless classification of light curves

Abstract

Not specified

Authors: S. D. Kügler, N. Gianniotis, K. L. Polsterer

Date Published: 25th Jun 2015

Publication Type: Journal

Autoencoding Time Series for Visualisation

Abstract

Not specified

Authors: N. Gianniotis, S. D. Kügler, P. Tino, K. L. Polsterer, R. Misra

Date Published: 1st May 2015

Publication Type: InProceedings

Determining spectroscopic redshifts by using k nearest neighbor regression. I. Description of method and analysis

Abstract

Not specified

Authors: S. D. Kügler, K. Polsterer, M. Hoecker

Date Published: 1st Apr 2015

Publication Type: Journal

Clustering of Complex Data-Sets Using Fractal Similarity Measures and Uncertainties

Abstract

Not specified

Authors: Maximilian Hoecker, Kai Lars Polsterer, Sven Dennis Kugler, Vincent Heuveline

Date Published: 2015

Publication Type: InProceedings

Improving the performance of photometric regression models via massive parallel feature selection

Abstract (Expand)

Regression tasks are common in astronomy, for instance, the estimation of the redshift or the metallicity of galaxies. Generating regression models, however, is often hindered by the heterogeneity of … the available input catalogs, which leads to missing data and/or features of differing explanatory power. In this work, we show how simple but effective feature selection schemes from data mining can be used to significantly improve the performance of regression models for photometric redshift and metallicity estimation (even without any particular knowledge of the input parameters' physical properties). Our framework tests huge amounts of possible feature combinations. Since corresponding (single-core) implementations are computationally very demanding, we make use of the massive computational resources provided by nowadays graphics processing units to significantly reduce the overall runtime. This renders an exhaustive search possible, as we demonstrate in our experimental evaluation. We conclude the work by discussing further applications of our approach in the context of large-scale astronomical learning settings.

Authors: K. L. Polsterer, F. Gieseke, Christian Igel, Tomotsugu Goto

Date Published: 1st May 2014

Publication Type: InProceedings

Powered by
 (v.1.16.0)
About HITS Publication SEEK | About HITS-Publication-SEEK | Funding and Programmes | Credits
Copyright © 2008 - 2024 The University of Manchester and HITS gGmbH