Tilman Hartwig

Title: Machine Learning for Classification of Astronomical Data


I will give an overview of various machine learning methods
and their scientific applications. As one specific example, I will
present decision trees in more detail since they are a very efficient
method to classify astronomical data: a labelled training sample is
split according to available features by requiring that each split
minimises the information entropy of the assigned classes. This elegant
mathematical formulation allows us to construct decision trees with
supervised learning, which can then be applied to classify new observations.
Eventually, I will present recent results of my own research: by
classifying the chemical abundance patterns of metal-poor stars in the
Milky Way, we can derive the multiplicity of the first generation of
stars in the Universe. Furthermore, this approach provides the feature
importance to identify crucial chemical elements to classify metal-poor
stars, which can be used to optimise future spectroscopic surveys.

トップ   編集 凍結 差分 バックアップ 添付 複製 名前変更 リロード   新規 一覧 単語検索 最終更新   ヘルプ   最終更新のRSS
Last-modified: 2019-06-06 (木) 15:22:54 (678d)