Machine Learning for Solar Studies
- Autores: Illarionov E.A1,2, Sadykov V.M3
-
Afiliações:
- Lomonosov Moscow State University
- Moscow Center for Fundamental and Applied Mathematics
- Georgia State University
- Edição: Nº 4 (2021)
- Páginas: 35-45
- Seção: Articles
- URL: https://journals.eco-vector.com/0044-3948/article/view/630962
- DOI: https://doi.org/10.7868/S0044394821040034
- ID: 630962
Citar
Texto integral
![Acesso aberto](https://journals.eco-vector.com/lib/pkp/templates/images/icons/text_open.png)
![Acesso é fechado](https://journals.eco-vector.com/lib/pkp/templates/images/icons/text_unlock.png)
![Acesso é fechado](https://journals.eco-vector.com/lib/pkp/templates/images/icons/text_lock.png)
Resumo
In the paper we show several examples, when the machine learning algorithms help to solve the problems in solar studies and what are the main features of this approach. We discuss convolutional neural networks; cluster analysis; and binary classification.
Sobre autores
E. Illarionov
Lomonosov Moscow State University; Moscow Center for Fundamental and Applied MathematicsMoscow, Russia; Moscow, Russia
V. Sadykov
Georgia State UniversityAtlanta, GA, USA
Bibliografia
- Silver D. et al. Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm, 2017, arxiv:1712.01815
- Витинский Ю.И. Солнечная активность. 2-е изд. М.: Наука, 1983.
- Camporeale E., Wing S., Johnson J. Machine Learning Techniques for Space Weather, 2018.
- Murphy K. Machine Learning: A Probabilistic Perspective, 2012. MIT Press, ISBN: 9780262018029
- Bishop C. Pattern Recognition and Machine Learning, 2006. Springer-Verlag New York. ISBN978-0-387-31073-2
Arquivos suplementares
![](/img/style/loading.gif)