文章基本信息

标题：Ordered Weighted Averaging (OWA), Decision Making under Uncertainty, and Deep Learning: How Is This All Related?
本地全文：下载
作者：Vladik Kreinovich
期刊名称：Information
电子版ISSN：2078-2489
出版年度：2022
卷号：13
期号：2
页码：82
DOI：10.3390/info13020082
语种：English
出版社：MDPI Publishing
摘要：Among many research areas to which Ron Yager contributed are decision making under uncertainty (in particular, under interval and fuzzy uncertainty) and aggregation—where he proposed, analyzed, and utilized ordered weighted averaging (OWA). The OWA algorithm itself provides only a specific type of data aggregation. However, it turns out that if we allow several OWA stages, one after another, we obtain a scheme with a universal approximation property—moreover, a scheme which is perfectly equivalent to modern ReLU-based deep neural networks. In this sense, Ron Yager can be viewed as a (grand)father of ReLU-based deep learning. We also recall that the existing schemes for decision making under uncertainty are also naturally interpretable in OWA terms.