Publication: Classification of noise sources in LIGO gravitational wave observations using deep neural networks and model explainability analysis
Loading...
Identifiers
Publication date
2021
Defense date
2021-02
Authors
Advisors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
This document uses state of the art image classification techniques to automate the detection
of noise sources in gravitational wave observations from the Laser Interferometer
Gravitational-Wave Observatory (LIGO). Additionally, it analyzes the resulting model using
post-hoc local interpretation methodologies with the intent of defining possible paths
of improvement.
Description
Keywords
Redes neuronales, Análisis de datos