Abstract
Quantizers play a critical role in digital signal processing systems. Recent works have shown that the performance of acquiring multiple analog signals using scalar analog-to-digital converters (ADCs) can be significantly improved by processing the signals prior to quantization. However, the design of such hybrid quantizers is quite complex, and their implementation requires complete knowledge of the statistical model of the analog signal. In this work we design data-driven task-oriented quantization systems with scalar ADCs, which determine their analog-to-digital mapping using deep learning tools. These mappings are designed to facilitate the task of recovering underlying information from the quantized signals. By using deep learning, we circumvent the need to explicitly recover the system model and to find the proper quantization rule for it. Our main target application is multiple-input multiple-output (MIMO) communication receivers, which simultaneously acquire a set of analog signals, and are commonly subject to constraints on the number of bits. Our results indicate that, in a MIMO channel estimation setup, the proposed deep task-bask quantizer is capable of approaching the optimal performance limits dictated by indirect rate-distortion theory, achievable using vector quantizers and requiring complete knowledge of the underlying statistical model. Furthermore, for a symbol detection scenario, it is demonstrated that the proposed approach can realize reliable bit-efficient hybrid MIMO receivers capable of setting their quantization rule in light of the task.
Highlights
Accepted: 12 January 2021Digital signal processing systems operate on finite-bit representation of continuousamplitude physical signals
Even when the deep neural network (DNN)-based quantizer is trained with samples taken from setups with different signal-to-noise ratio (SNR), it is still able to approach the performance of the optimal task-based quantizers with analog-to-digital converters (ADCs) for varying SNRs, which is within a small gap of the fundamental performance limits
We focus on two tasks encountered in such setups: The first is channel estimation detailed in Section 4.1, for which we are capable of quantifying the performance gap of our system from optimality as well as comparing it to model-based designs
Summary
Accepted: 12 January 2021Digital signal processing systems operate on finite-bit representation of continuousamplitude physical signals. The task of the system is to recover some underlying parameters, and not to accurately represent the observed signal In these cases, it was shown that by accounting for the system task in the design of the quantizers, namely by using task-based quantization, the accuracy in carrying out the task can be improved without increasing the number of bits used [4,5,6,7]. It was shown that by accounting for the system task in the design of the quantizers, namely by using task-based quantization, the accuracy in carrying out the task can be improved without increasing the number of bits used [4,5,6,7] Such task-based quantization was shown to improve performance in channel estimation [8,9] and target identification in multiple-input multiple-output (MIMO) radar [10], when operating under tight bit budgets
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
