A Comparative Study of Estimating Supermassive Black Hole Masses: Linear Regression versus Deep Learning Methods
- Bachelorarbeit -
Description:
The purpose of this thesis is to use linear regression and deep learning models to estimate the masses of supermassive black holes. For this application, filtered AGN data from the SDSS dataset will be used. The aim is to explore the superiorities of both methods against each other and provide information for future research.
Deep learning methods are not employed for the dataset that we have used. We aim to try out different deep learning models to see if they fit the job. There are some studies using lasso regression for the same data. We will also reimplement this approach for comparison, as well as linear regression models with other regularizations. As the final product, a comparison of all the methods that will be tried out will be presented.
Anforderungen/Kenntnisse:
Machine Learning
Bearbeitung:
L. Weinknecht
Betreuung:
Prof. Dr. rer. nat. habil. Sven Groppe
Institut für Informationssysteme
Ratzeburger Allee 160 ( Gebäude 64 - 2. OG)
23562 Lübeck
Telefon: 0451 / 3101 5706
