Neural equalization of communication channels

Abstract

The authors describe the use of a dynamic model of the biological neuron called the dynamic neural unit (DNU) and examine briefly how it can be used in a channel equalization problem. The DNU, which comprises an infinite impulse response (IIR) structure followed by a nonlinear activation function, is used to obtain an inverse model of unknown channel dynamics. Once a unity mapping from output to input is achieved, the channel passes the source signal with almost no distortion to the receiver end. The DNU architecture and algorithm are described.<>