1-D multiplierless phase retrieval using recurrent neural networks

Abstract

The phase retrieval problem arises when the phase of a signal is apparently lost or impractical to measure and must be reconstructed from only the magnitude of its Fourier transform. In this paper we propose a multiplierless recurrent neural network for solving this problem. The recurrent neural network incorporates the constants related to the real and… (More)

4 Figures and Tables

Topics

  • Presentations referencing similar topics