ViterbiNet: A Deep Learning Based Viterbi Algorithm for Symbol Detection

• Published in: IEEE transactions on wireless communications Vol. 19; no. 5; pp. 3319 - 3331
• Main Authors: Shlezinger, Nir, Farsad, Nariman, Eldar, Yonina C., Goldsmith, Andrea J.
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.05.2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Artificial neural networks; Channel models; Communications systems; Decoding; Deep learning; Detectors; machine learning (ML); Receivers; Robustness (mathematics); Symbol detection; Task analysis; Training; Viterbi algorithm; Viterbi algorithm detectors
• ISSN: 1536-1276; 1558-2248
• DOI: 10.1109/TWC.2020.2972352

Symbol detection plays an important role in the implementation of digital receivers. In this work, we propose ViterbiNet, which is a data-driven symbol detector that does not require channel state information (CSI). ViterbiNet is obtained by integrating deep neural networks (DNNs) into the Viterbi algorithm. We identify the specific parts of the Viterbi algorithm that depend on the channel model, and design a DNN to implement only those computations, leaving the rest of the algorithm structure intact. We then propose a meta-learning based approach to train ViterbiNet online based on recent decisions, allowing the receiver to track dynamic channel conditions without requiring new training samples for every coherence block. Our numerical evaluations demonstrate that the performance of ViterbiNet, which is ignorant of the CSI, approaches that of the CSI-based Viterbi algorithm, and is capable of tracking time-varying channels without needing instantaneous CSI or additional training data. Moreover, unlike conventional Viterbi detection, ViterbiNet is robust to CSI uncertainty, and it can be reliably implemented in complex channel models with constrained computational burden. More broadly, our results demonstrate the conceptual benefit of designing communication systems that integrate DNNs into established algorithms.