Deep Blind One-Bit Signal Recovery

Abstract

In this paper, we consider blind one-bit signal recovery, where the linear measurements of the signal are quantized to single bits and the signal is to be recovered without knowledge of the measurement matrix, noise statistics and the quantization thresholds. We propose two deep learning based methods, one based on a multi -layer perceptron architecture and the other based on the long short-term memory architecture. The two neural architectures are inspired by the recurrent calculation of the gradient descent method to solve the maximum likelihood detection. By the universal approximation theorem for deep neural networks, there exist network realizations for the proposed architectures such that they can achieve at least the same effect of the gradient descent solver. The performance of the proposed schemes is compared with a recently proposed deep learning based signal recovery framework. Experiments show that our proposed blind one-bit signal recovery schemes achieve comparable signal reconstruction performance with a much lower complexity even without the knowledge of the measurement matrix.