Deep Learning for Communication over Dispersive Nonlinear Channels: Performance and Comparison with Classical Digital Signal Processing

Abstract

In this paper, we apply deep learning for communication over dispersive channels with power detection, as encountered in low-cost optical intensity modulation/direct detection (IM/DD) links. We consider an autoencoder based on the recently proposed sliding window bidirectional recurrent neural network (SBRNN) design to realize the transceiver for optical IM/DD communication. We show that its performance can be improved by introducing a weighted sequence estimation scheme at the receiver. Moreover, we perform bit-to-symbol mapping optimization to reduce the bit-error rate (BER) of the system. Furthermore, we carry out a detailed comparison with classical schemes based on pulse-amplitude modulation and maximum likelihood sequence detection (MLSD). Our investigation shows that for a reference 42\,Gb/s transmission, the SBRNN autoencoder achieves a BER performance comparable to MLSD, when both systems account for the same amount of memory. In contrast to MLSD, the SBRNN performance is achieved without incurring a computational complexity exponentially growing with the processed memory.

Invited paper at Allerton 2019 Conference on Communication, Control and Computing

References in corpus (5)

• Adam: A Method for Stochastic Optimization
• Deep Learning-Based Communication Over the Air
• End-to-end Deep Learning of Optical Fiber Communications
• Neural Network Detection of Data Sequences in Communication Systems
• Applying Neural Networks in Optical Communication Systems: Possible Pitfalls

Cited by in corpus (2)

• End-to-End Learning for VCSEL-based Optical Interconnects: State-of-the-Art, Challenges, and Opportunities
• Optical Fiber Communication Systems Based on End-to-End Deep Learning