Deep Optimization of Relay Networks-Using Relays as Neurons

Abstract

We consider the optimization of a network with amplify-and-forward relays. Observing that the power limit at each relay presents a non-linear transfer function, we focus on the similarity between relay networks and neural networks. Thus, we treat relays as neurons, and use deep learning tools to achieve better optimization of the network. Deep learning optimization allows relays to exploit their non-linear regime (and hence increase their transmission power) while still avoiding harmful distortion. Moreover, copying the computational capabilities of neural networks, we can take advantage of the non-linearities and implement parts of the received functionalities over the relay network. By treating each relay element as a node in a deep neural network, our optimization results in huge gains over traditional relay optimization, and also allows the use of simpler receivers.