Deep Learning for Photo-Z Redshift Reconstruction

Student: Shayakhmetov Rim

Educational Programme: Data Science (Master)

Year of Graduation: 2017

Large amount of astronomical data enables machine learning to improve accuracy of predictions on many problems. Redshift estimation is an essential problem in astronomy that can be drastically improved by deep learning algorithms. We propose using not only galaxies, but all objects in the training set, thus alleviating selection bias. In our work we extend the baseline predictions by gradient boosting, and explore how deep learning can improve it. We show that deep learning can uncover complex feature interactions not only on raw images but on different measures of standard object features, outperforming baseline. In addition, pre-training the network on huge amount of unlabeled data did not improve prediction accuracy.

Student Theses at HSE must be completed in accordance with the University Rules and regulations specified by each educational programme.

Summaries of all theses must be published and made freely available on the HSE website.

The full text of a thesis can be published in open access on the HSE website only if the authoring student (copyright holder) agrees, or, if the thesis was written by a team of students, if all the co-authors (copyright holders) agree. After a thesis is published on the HSE website, it obtains the status of an online publication.

Student theses are objects of copyright and their use is subject to limitations in accordance with the Russian Federation’s law on intellectual property.

In the event that a thesis is quoted or otherwise used, reference to the author’s name and the source of quotation is required.

Search all student theses