This is my first experience of analysing huge data using Machine Learning.

Data are taken from the Sloan Digital Sky Survey (SDSS), in three categories: Star, Galaxy, Quasar. And the model is built on top of Keras library.

[UPDATE] Enhanced result (2085 wrong predicted among 317520 test data):

Results on range of the Abell catalogue numbers 13-1991:

Results on the range of the Abell catalogue numbers 13-1991 and numbers 2029-4059: