Article Preview
TopBackground
The idea of generative-adversarial natural networks (GANs) was proposed by J. Goodfellow of the University of Montreal (Goodfellow et al., 2014). During literally a couple of years, this method has found its application in the tasks of semantic image segmentation, medical information analysis, material recognition, time series analysis (Luc et al., 2016; Che et al., 2017; Erickson et al., 2017; Esteban et al., 2017; Chen et al., 2016; Hinton & Salakhutdinov, 2006; Mescheder et al., 2017; Dumoulin et al., 2016; Donahue et al., 2016; Li et al., 2017; Reed et al., 2016; Isola et al., 2016; Ledig et al., 2016; Ren et al., 2015; Lee et al., 2016).