VGU RESEARCH REPOSITORY
Please use this identifier to cite or link to this item:
https://epub.vgu.edu.vn/handle/dlibvgu/549| Title: | Galaxy images classification | Authors: | Dinh Cong Minh | Keywords: | Galaxy challenge;Machine learning | Issue Date: | 2014 | Publisher: | Vietnamese-German University | Abstract: | From 20th December 2013 to 4th April 2014, Kaggle held the “Galaxy Zoo, A Galaxy Challenge” competition [1], in which the competitors are asked to classify over 60000 images of galaxies into their classes. Prior to this competition, the task is done by a crowd-source project, which use human effort to manually classify the galaxy images. Now, with the data collected from the previous project, the task is to reproduce the results, which are also provided by the galaxy zoo organization. In this bachelor thesis, I will not try to build a perfect model for this task, which is outside of the scope of this thesis. I will rather try to solve a simplified task to demonstrate my knowledge in the machine learning and data science, as well as solving the task with an acceptable results. The main objectives of the project are: + Proposed a simplified version of the Galaxy Challenge + Review the fundamental theories in the field of machine learning + Implement a model which can solve the challenge with acceptable results |
URI(1): | http://epub.vgu.edu.vn/handle/dlibvgu/549 | Rights: | Attribution-NonCommercial 4.0 International |
| Appears in Collections: | Electrical Engineering and Information Technology (EEIT) |
Files in This Item:
| File | Description | Size | Format | Existing users please Login |
|---|---|---|---|---|
| Galaxy images classification.pdf | 1.01 MB | Adobe PDF |
Page view(s)
58
checked on Aug 23, 2025
Download(s)
13
checked on Aug 23, 2025
Google ScholarTM
Check
This item is licensed under a Creative Commons License