# Widely Linear Complex-valued Autoencoder: Dealing with Noncircularity in Generative-Discriminative Models

5 Mar 2019Zeyang YuShengxi LiDanilo Mandic

We propose a new structure for the complex-valued autoencoder by introducing additional degrees of freedom into its design through a widely linear (WL) transform. The corresponding widely linear backpropagation algorithm is also developed using the $\mathbb{CR}$ calculus, to unify the gradient calculation of the cost function and the underlying WL model... (read more)

PDF Abstract