Learning morphological maps of galaxies with unsupervised regression

Oliver Kramer; Fabian Gieseke; Kai Lars Polsterer

doi:10.1016/j.eswa.2012.12.002

Learning morphological maps of galaxies with unsupervised regression

Oliver Kramer, Fabian Gieseke, Kai Lars Polsterer

2 Citations (Scopus)

Abstract

Hubble's morphological classification of galaxies has found broad acceptance in astronomy since decades. Numerous extensions have been proposed in the past, mostly based on galaxy prototypes. In this work, we automatically learn morphological maps of galaxies with unsupervised machine learning methods that preserve neighborhood relations and data space distances. For this sake, we focus on a stochastic variant of unsupervised nearest neighbors (UNN) for arranging galaxy prototypes on a two-dimensional map. UNN regression is the unsupervised counterpart of nearest neighbor regression for dimensionally reduction. In the experimental part of this article, we visualize the embeddings and compare the learning results achieved by various UNN parameterizations and related dimensionality reduction methods.

Original language	English
Journal	Expert Systems with Applications
Volume	40
Issue number	8
Pages (from-to)	2841-2844
Number of pages	4
ISSN	0957-4174
DOIs	https://doi.org/10.1016/j.eswa.2012.12.002
Publication status	Published - 15 Jun 2013
Externally published	Yes

Access to Document

10.1016/j.eswa.2012.12.002

Cite this

@article{24c26c49e5b04e34837bd63e45d1037f,

title = "Learning morphological maps of galaxies with unsupervised regression",

abstract = "Hubble's morphological classification of galaxies has found broad acceptance in astronomy since decades. Numerous extensions have been proposed in the past, mostly based on galaxy prototypes. In this work, we automatically learn morphological maps of galaxies with unsupervised machine learning methods that preserve neighborhood relations and data space distances. For this sake, we focus on a stochastic variant of unsupervised nearest neighbors (UNN) for arranging galaxy prototypes on a two-dimensional map. UNN regression is the unsupervised counterpart of nearest neighbor regression for dimensionally reduction. In the experimental part of this article, we visualize the embeddings and compare the learning results achieved by various UNN parameterizations and related dimensionality reduction methods.",

author = "Oliver Kramer and Fabian Gieseke and Polsterer, {Kai Lars}",

year = "2013",

month = jun,

day = "15",

doi = "10.1016/j.eswa.2012.12.002",

language = "English",

volume = "40",

pages = "2841--2844",

journal = "Expert Systems with Applications",

issn = "0957-4174",

publisher = "Pergamon Press",

number = "8",

}

TY - JOUR

T1 - Learning morphological maps of galaxies with unsupervised regression

AU - Kramer, Oliver

AU - Gieseke, Fabian

AU - Polsterer, Kai Lars

PY - 2013/6/15

Y1 - 2013/6/15

N2 - Hubble's morphological classification of galaxies has found broad acceptance in astronomy since decades. Numerous extensions have been proposed in the past, mostly based on galaxy prototypes. In this work, we automatically learn morphological maps of galaxies with unsupervised machine learning methods that preserve neighborhood relations and data space distances. For this sake, we focus on a stochastic variant of unsupervised nearest neighbors (UNN) for arranging galaxy prototypes on a two-dimensional map. UNN regression is the unsupervised counterpart of nearest neighbor regression for dimensionally reduction. In the experimental part of this article, we visualize the embeddings and compare the learning results achieved by various UNN parameterizations and related dimensionality reduction methods.

AB - Hubble's morphological classification of galaxies has found broad acceptance in astronomy since decades. Numerous extensions have been proposed in the past, mostly based on galaxy prototypes. In this work, we automatically learn morphological maps of galaxies with unsupervised machine learning methods that preserve neighborhood relations and data space distances. For this sake, we focus on a stochastic variant of unsupervised nearest neighbors (UNN) for arranging galaxy prototypes on a two-dimensional map. UNN regression is the unsupervised counterpart of nearest neighbor regression for dimensionally reduction. In the experimental part of this article, we visualize the embeddings and compare the learning results achieved by various UNN parameterizations and related dimensionality reduction methods.

U2 - 10.1016/j.eswa.2012.12.002

DO - 10.1016/j.eswa.2012.12.002

M3 - Journal article

SN - 0957-4174

VL - 40

SP - 2841

EP - 2844

JO - Expert Systems with Applications

JF - Expert Systems with Applications

IS - 8

ER -

Learning morphological maps of galaxies with unsupervised regression

Abstract

Access to Document

Fingerprint

Cite this