# ViterbiNet: A Deep Learning Based Viterbi Algorithm for Symbol Detection

arXiv: https://arxiv.org/abs/1905.10750 · HTML: https://mlsanity.com/paper/1905.10750/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 May 2019.

## Built on by (most cited first, 25 of 25)

- [KalmanNet: Neural Network Aided Kalman Filtering for Partially Known Dynamics](https://mlsanity.com/paper/2107.10043/) (2021)
- [Less Data, More Knowledge: Building Next Generation Semantic Communication Networks](https://mlsanity.com/paper/2211.14343/) (2022)
- [Theoretical Perspectives on Deep Learning Methods in Inverse Problems](https://mlsanity.com/paper/2206.14373/) (2022)
- [Unsupervised Learned Kalman Filtering](https://mlsanity.com/paper/2110.09005/) (2021)
- [Generative AI for Physical Layer Communications: A Survey](https://mlsanity.com/paper/2312.05594/) (2023)
- [Real-time Outdoor Localization Using Radio Maps: A Deep Learning Approach](https://mlsanity.com/paper/2106.12556/) (2021)
- [LoRD-Net: Unfolded Deep Detection Network with Low-Resolution Receivers](https://mlsanity.com/paper/2102.02993/) (2021)
- [Waveform Learning for Next-Generation Wireless Communication Systems](https://mlsanity.com/paper/2109.00998/) (2021)
- [Model-Based Machine Learning for Communications](https://mlsanity.com/paper/2101.04726/) (2021)
- [Score-based Source Separation with Applications to Digital Communication Signals](https://mlsanity.com/paper/2306.14411/) (2023)
- [Blind Channel Estimation and Joint Symbol Detection with Data-Driven Factor Graphs](https://mlsanity.com/paper/2401.12627/) (2024)
- [Two-Timescale End-to-End Learning for Channel Acquisition and Hybrid Precoding](https://mlsanity.com/paper/2110.12059/) (2021)
- [DDPG-Driven Deep-Unfolding with Adaptive Depth for Channel Estimation with Sparse Bayesian Learning](https://mlsanity.com/paper/2201.08477/) (2022)
- [Nested Construction of Polar Codes via Transformers](https://mlsanity.com/paper/2401.17188/) (2024)
- [SICNN: Soft Interference Cancellation Inspired Neural Network Equalizers](https://mlsanity.com/paper/2308.12591/) (2023)
- [Deep Learning-Based Detection for Marker Codes over Insertion and Deletion Channels](https://mlsanity.com/paper/2401.01155/) (2024)
- [Data-Driven Symbol Detection for Intersymbol Interference Channels with Bursty Impulsive Noise](https://mlsanity.com/paper/2405.10814/) (2024)
- [RAN Cortex: Memory-Augmented Intelligence for Context-Aware Decision-Making in AI-Native Networks](https://mlsanity.com/paper/2505.07842/) (2025)
- [A Glimpse of Physical Layer Decision Mechanisms: Facts, Challenges, and Remedies](https://mlsanity.com/paper/2102.07258/) (2021)
- [Online Optimization for Learning to Communicate over Time-Correlated Channels](https://mlsanity.com/paper/2409.00575/) (2024)
- [Transfer-based Adversarial Poisoning Attacks for Online (MIMO-)Deep Receviers](https://mlsanity.com/paper/2409.02430/) (2024)
- [L-SR1: Learned Symmetric-Rank-One Preconditioning](https://mlsanity.com/paper/2508.12270/) (2025)
- [Data-Driven Deep MIMO Detection:Network Architectures and Generalization Analysis](https://mlsanity.com/paper/2602.20178/) (2026)
- [Pre-Whitening and BCJR Posterior Distillation for Bi-LSTM Detection in Faster-than-Nyquist Signaling](https://mlsanity.com/paper/2609.07762/) (2026)
- [Geometric Inductive Biases for Semi-Supervised Equalization: The Constellation-Aware Transformer](https://mlsanity.com/paper/2609.33695/) (2026)

## Abstract (arXiv)

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 are channel-model-based, 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 to that integrate DNNs into established algorithms.