Neural Networks Based Domain Adaptation in Spectroscopic Sky Surveys

Fuente: Zenodo
Guardado en:
Detalles Bibliográficos
Autor principal: Podsztavek, Ondřej
Formato: Recurso digital
Lenguaje:inglés
Publicado: Zenodo 2020
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866902299910078464
author Podsztavek, Ondřej
author_facet Podsztavek, Ondřej
contents <p>We present an analysis of the impact of neural-based domain adaptation in astronomical spectroscopy. Domain adaptation addresses the problem of applying prior knowledge to a new data of interest. Therefore, we selected a problem of quasar identification in the Large Sky Area Multi-Object Fiber Spectroscopic Telescope survey using labelled data from the Sloan Digital Sky Survey. We choose to experiment with four neural models for domain adaptation: Deep Domain Confusion, Deep Correlation Alignment, Domain-Adversarial Network and Deep Reconstruction-Classification Network. However, our experiments reveal that these model cannot improve classification performance in comparison to a convolutional neural network that does not consider domain adaptation. Using dimensionality reduction, statistics of the selected methods and misclassifications, we show that the domain adaptation methods are not robust enough to be applied to the complex and dirty astronomical data.</p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_3685516
institution Zenodo
language eng
publishDate 2020
publisher Zenodo
record_format zenodo
spellingShingle Neural Networks Based Domain Adaptation in Spectroscopic Sky Surveys
Podsztavek, Ondřej
domain adaptation
neural networks
deep learning
astronomical spectroscopy
astronomy
<p>We present an analysis of the impact of neural-based domain adaptation in astronomical spectroscopy. Domain adaptation addresses the problem of applying prior knowledge to a new data of interest. Therefore, we selected a problem of quasar identification in the Large Sky Area Multi-Object Fiber Spectroscopic Telescope survey using labelled data from the Sloan Digital Sky Survey. We choose to experiment with four neural models for domain adaptation: Deep Domain Confusion, Deep Correlation Alignment, Domain-Adversarial Network and Deep Reconstruction-Classification Network. However, our experiments reveal that these model cannot improve classification performance in comparison to a convolutional neural network that does not consider domain adaptation. Using dimensionality reduction, statistics of the selected methods and misclassifications, we show that the domain adaptation methods are not robust enough to be applied to the complex and dirty astronomical data.</p>
title Neural Networks Based Domain Adaptation in Spectroscopic Sky Surveys
topic domain adaptation
neural networks
deep learning
astronomical spectroscopy
astronomy
url https://doi.org/10.5281/zenodo.3685516