Learning with explainable trees

doi:10.1038/s42256-019-0142-0

2020-01-17

PRE

Wojciech Samek *

DOI：10.1038/s42256-019-0142-0

原文链接

原文求助

摘要

En 中文

Tree-based models are among the most popular and successful machine learning algorithms in practice. New tools allow us to explain the predictions and gain insight into the global behaviour of these models.

AI总结

对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

Nature Machine Intelligence

IF:

23.9

论文数:

1.3K

被引数:

1.5W

机构

fraunhofer gesellschaft

学者数:

1.6W

论文数: 1.2W

被引数: 24

引用论文

Unmasking Clever Hans predictors and assessing what machines really learn 揭开聪明的汉斯预测器并评估机器真正学到的东西

NATURE COMMUNICATIONS

IF15.7

2019-03-11

646

OAAI

Lapuschkin, Sebastian; Waeldchen, Stephan; Binder, Alexander; Montavon, Gregoire; Samek, Wojciech; Mueller, Klaus-Robert

From local explanations to global understanding with explainable AI for trees 用可解释的人工智能从局部解释到全局理解

NATURE MACHINE INTELLIGENCE

IF23.9

2020-01-17

3.3K

OAAI

Lundberg, Scott M.; Erion, Gabriel; Chen, Hugh; DeGrave, Alex; Prutkin, Jordan M.; Nair, Bala; Katz, Ronit; Himmelfarb, Jonathan; Bansal, Nisha; Lee, Su-In

Fatty acid collectors for phosphate flotation and their adsorption behavior using QCM-D

International Journal of Mineral Processing

IF0

2010-07-01

PREAI

J. Kou; D. Tao; G. Xu