Ordered Weighted Averaging (OWA), Decision Making Under Uncertainty, and Deep Learning: How Is This All Related?
Keyword(s):
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 the use of Ordered Weighted Averaging (OWA). The OWA algorithm itself provides only a specific type of data aggregation. However, it turns out that if we allows several OWA stages one after another, we get a scheme with a universal approximation property – moreover, a scheme which is perfectly equivalent to deep neural networks. In this sense, Ron Yager can be viewed as a (grand)father of deep learning. We also show that the existing schemes for decision making under uncertainty are also naturally interpretable in OWA terms.
2013 ◽
Vol 21
(2)
◽
pp. 247-262
◽
2012 ◽
Vol 25
(1)
◽
pp. 72-81
◽
1996 ◽
Vol 04
(01)
◽
pp. 1-25
◽
2017 ◽
Vol 5
(2)
◽
pp. 148-162
◽
2017 ◽
Vol 33
(3)
◽
pp. 514-528
◽
2014 ◽
Vol 11
(2)
◽
pp. 839-857
◽
2012 ◽
Vol 9
(1)
◽
pp. 357-380
◽