BriefGPT.xyz
Jan, 2019
适应于时间序列的CNN用于超新星分类
A CNN adapted to time series for the classification of Supernovae
HTML
PDF
Anthony Brunel, Johanna Pasquet, Jérôme Pasquet, Nancy Rodriguez, Frédéric Comby...
TL;DR
本文研究了宇宙学中通过机器学习进行分类的方法，在超新星现象中，使用卷积神经网络进行I.a超新星与非I.a超新星的二元分类，提出两种卷积神经网络分别应对超新星光变曲线的时间序列和数据稀疏的问题，并达到了当前最先进的水平。
Abstract
Cosmologists are facing the problem of the analysis of a huge quantity of data when observing the sky. The methods used in
cosmology
are, for the most of them, relying on astrophysical models, and thus, for the
classifi
→