paper.md

title	tags	authors	affiliations	date	bibliography
MiraPy: Python Package for Deep Learning in Astronomy	Python astronomy deep learning machine learning image reconstruction variable star classification curve fitting	name orcid affiliation Swapnil Sharma 0000-0002-0329-9314 1 name affiliation Akhil Singhal 1 name affiliation Arnav Bhavsar 1	name index Indian Institute of Technology, Mandi 1	1 July 2019	paper.bib

Summary

MiraPy is a Python package[astropy:2018] for Deep Learning in Astronomy. It is built using Keras [@chollet2015keras] for developing ML models to run on CPU and GPU seamlessly. The aim is to make applying machine learning techniques on astronomical data easy for astronomers, researchers and students.

MiraPy can be used for problem solving using ML techniques and will continue to grow to tackle new problems in Astronomy.

Applications

Following are the experiments that you can perform right now:

• Classification of X-Ray Binaries using neural network [@Gopalan_2015]
• Astronomical Image Reconstruction using Autoencoder
• Classification of the first catalog of variable stars by ATLAS [@Heinze_2018]
• HTRU1 Pulsar Dataset Image Classification using Convolutional Neural Network [@10.1093/mnras/stu1188]
• OGLE Catalogue Variable Star Classification using Recurrent Neural Network (RNN) [@1810.09489]
• 2D and 3D visualization of feature sets using Principal Component Analysis (PCA) [@Barnes_2016]
• Curve Fitting using Autograd (basic implementation)

Acknowledgements

MiraPy is developed by Swapnil Sharma and Akhil Singhal as their final year 'Major Technical Project' under the guidance of Dr. Arnav Bhavsar at Indian Institute of Technology, Mandi. [@scikit-learn] [@scikit-image] [@scipy] [@oliphant2006guide] [@Hunter:2007]

References