Spectral SOM

Application of a Self-Organizing Map to the context of spectral analysis
Explore the docs (Coming Soon) »

Example · Report Bug · Request Feature

Table of Contents

1. About The Project
   • Built With
2. Example
3. Roadmap
4. License
5. Contact
6. Acknowledgments

About The Project

Python tool for the application of a machine learning technique, the so-called Self-Organizing Maps of Features, to the world of spectral analysis. This aims at speeding up the process of categorization and Gaussian decomposition through the means of pattern e.g. similarities recognition in the implemented neuron network. This idea was first introduced in a 1990 paper by T. Kohonen, pointing out the astonishing ways the neurons in the human brain organize themselves when reacting to sensorial input. This work is implemented in the context of the Bachelor Thesis in Astronomy and Astrophysics @ the University of Vienna by Simone Spedicato.

Built With

• Python

Usage

Coming Soon...

For more examples, please refer to the Documentation(Coming Soon)

Roadmap

• General improvements
  • Faster execution
  • Better interface with the user
  • Better input handling
  • Further handling of the worse fits
• Study of absorption line profiles
• Study of fine and hyper-fine profiles

See the open issues for a full list of proposed features (and known issues).

License

Distributed under the MIT License. See LICENSE.txt for more information.

Contact

Simone Spedicato - simonespedicatospf@gmail.com

Project Link: https://github.com/SimoneSped/SOM

Acknowledgments

• EMERGE Group @ Astronomy Institute of the University of Vienna

(back to top)