gbt-HIPS: Explaining the Classifications of Gradient Boosted Tree Ensembles

This research presents <i>Gradient Boosted Tree High Importance Path Snippets</i> (gbt-HIPS), a novel, heuristic method for explaining gradient boosted tree (GBT) classification models by extracting a single classification rule (CR) from the ensemble of decision trees that make up the GBT model. Thi...

詳細記述

書誌詳細

主要な著者:	Julian Hatwell, Mohamed Medhat Gaber, R. Muhammad Atif Azad
フォーマット:	Artigo
言語:	Inglês
出版事項:	MDPI AG 2021-03-01
シリーズ:	Applied Sciences
主題:	explainable artificial intelligence human-understandable AI systems gradient boosting black box problem machine learning interpretability
オンライン･アクセス:	https://www.mdpi.com/2076-3417/11/6/2511
タグ:	タグ追加 タグなし, このレコードへの初めてのタグを付けませんか!