no code implementations • 2 Sep 2020 • Danilo Vasconcellos Vargas, Bingli Liao, Takahiro Kanzaki
Thus, $\varphi$DNNs reveal that input recreation has strong benefits for artificial neural networks similar to biological ones, shedding light into the importance of purposely corrupting the input as well as pioneering an area of perception models based on GANs and autoencoders for robust recognition in artificial intelligence.