End-to-end Deep Learning of Optical Fiber Communications

Abstract

In this paper, we implement an optical fiber communication system as an end-to-end deep neural network, including the complete chain of transmitter, channel model, and receiver. This approach enables the optimization of the transceiver in a single end-to-end process. We illustrate the benefits of this method by applying it to intensity modulation/direct detection (IM/DD) systems and show that we can achieve bit error rates below the 6.7\% hard-decision forward error correction (HD-FEC) threshold. We model all componentry of the transmitter and receiver, as well as the fiber channel, and apply deep learning to find transmitter and receiver configurations minimizing the symbol error rate. We propose and verify in simulations a training method that yields robust and flexible transceivers that allow---without reconfiguration---reliable transmission over a large range of link dispersions. The results from end-to-end deep learning are successfully verified for the first time in an experiment. In particular, we achieve information rates of 42\,Gb/s below the HD-FEC threshold at distances beyond 40\,km. We find that our results outperform conventional IM/DD solutions based on 2 and 4 level pulse amplitude modulation (PAM2/PAM4) with feedforward equalization (FFE) at the receiver. Our study is the first step towards end-to-end deep learning-based optimization of optical fiber communication systems.

arXiv commentsubmitted to IEEE/OSA Journal of Lightwave Technology

References in corpus (3)

• Adam: A Method for Stochastic Optimization
• Deep Learning-Based Communication Over the Air
• Applying Neural Networks in Optical Communication Systems: Possible Pitfalls

Cited by in corpus (48)

• Deep learning for dynamic modeling and coded information storage of vector-soliton pulsations in mode-locked fiber lasers
• Compensation of Fiber Nonlinearities in Digital Coherent Systems Leveraging Long Short-Term Memory Neural Networks
• End-to-End Optimized Transmission over Dispersive Intensity-Modulated Channels Using Bidirectional Recurrent Neural Networks
• Artificial Neural Networks for Photonic Applications: From Algorithms to Implementation
• Deep Learning for Signal Demodulation in Physical Layer Wireless Communications: Prototype Platform, Open Dataset, and Analytics
• Does deep learning always outperform simple linear regression in optical imaging?
• Learning for Detection: MIMO-OFDM Symbol Detection through Downlink Pilots
• End-to-end optimization of coherent optical communications over the split-step Fourier method guided by the nonlinear Fourier transform theory
• End-to-End Learning for VCSEL-based Optical Interconnects: State-of-the-Art, Challenges, and Opportunities
• Geometric Constellation Shaping for Fiber-Optic Channels via End-to-End Learning
• End-to-End Learning of Geometrical Shaping Maximizing Generalized Mutual Information
• Model-Based Machine Learning for Joint Digital Backpropagation and PMD Compensation
• Principle-driven Fiber Transmission Model based on PINN Neural Network
• Deep Learning in Physical Layer: Review on Data Driven End-to-End Communication Systems and their Enabling Semantic Applications
• End-to-end Learning of a Constellation Shape Robust to Channel Condition Uncertainties
• AdaNN: Adaptive Neural Network-based Equalizer via Online Semi-supervised Learning
• Gradient-free training of autoencoders for non-differentiable communication channels
• End-to-end Optimization of Constellation Shaping for Wiener Phase Noise Channels with a Differentiable Blind Phase Search
• Geometric Constellation Shaping for Phase-noise Channels Using a Differentiable Blind Phase Search
• Towards Optimal Power Control via Ensembling Deep Neural Networks
• Deep Learning for Communication over Dispersive Nonlinear Channels: Performance and Comparison with Classical Digital Signal Processing
• An Interpretable Mapping from a Communication System to a Neural Network for Optimal Transceiver-Joint Equalization
• End-to-end Optimization of Optical Communication Systems based on Directly Modulated Lasers
• Wiener Filter for Short-Reach Fiber-Optic Links
• CMDNet: Learning a Probabilistic Relaxation of Discrete Variables for Soft Detection with Low Complexity
• Achievable Rates for Short-Reach Fiber-Optic Channels with Direct Detection
• Deep-learning Autoencoder for Coherent and Nonlinear Optical Communication
• DeepJSCC-f: Deep Joint Source-Channel Coding of Images with Feedback
• Optical Fiber Communication Systems Based on End-to-End Deep Learning
• Direct Detection Under Tukey Signalling
• Intelligent Radio Signal Processing: A Survey
• Achievable Information Rates for Nonlinear Fiber Communication via End-to-end Autoencoder Learning
• A Very Brief Introduction to Machine Learning With Applications to Communication Systems
• Inverse Design of All-dielectric Parallel-Plane Mirror Resonator
• On the Robustness of Deep Learning-aided Symbol Detectors to Varying Conditions and Imperfect Channel Knowledge
• Realtime Scheduling and Power Allocation Using Deep Neural Networks
• Deep Learning based Channel Estimation Algorithm over Time Selective Fading Channels
• Blind interactive learning of modulation schemes: Multi-agent cooperation without co-design
• A Novel Deep Neural Network Based Approach for Sparse Code Multiple Access
• Learning OFDM Waveforms with PAPR and ACLR Constraints
• Learning to Modulate for Non-coherent MIMO
• A Hybrid Approach combining ANN-based and Conventional Demapping in Communication for Efficient FPGA-Implementation
• Over-the-fiber Digital Predistortion Using Reinforcement Learning
• Three novel efficient Deep Learning-based approaches for compensating atmospheric turbulence in FSO communication system
• Deep Learning-Based Constellation Optimization for Physical Network Coding in Two-Way Relay Networks
• Learning Physical-Layer Communication with Quantized Feedback
• On Deep Learning for Radio Resource Management in A Non-stationary Radio Environment
• Symbol-Based Over-the-Air Digital Predistortion Using Reinforcement Learning