Authors:
Roger A. Hallman
1
;
2
and
George Cybenko
2
Affiliations:
1
Naval Information Warfare Center (NIWC) Pacific, San Diego, California, U.S.A.
;
2
Thayer School of Eningeering, Dartmouth College, Hanover, New Hampshire, U.S.A.
Keyword(s):
Data Deconflation, Deconvolution, Blind Source Separation, Cocktail Party Problem, Simple Data, Complex Data, Deep Learning, Deep Reinforcement Learning (DRL), Generative Adversarial Networks (GANs).
Abstract:
Data conflation refers to the superposition data produced by diverse processes resulting in complex, combined data objects. We define the data deconflation problem as the challenge of identifying and separating these complex data objects into their individual, constituent objects. Solutions to classical deconflation problems (e.g., the Cocktail Party Problem) use established linear algebra techniques, but it is not clear that those solutions are extendable to broader classes of conflated data objects. This paper surveys both classical and emerging data deconflation problems, as well as presenting an approach towards a general solution utilizing deep reinforcement learning and generative adversarial networks.