Multi-Symbol Output Long Short-Term Memory Neural Network Equalizer For 200+ Gbps IM/DD System

Sang, Bohan; Zhang, Jiao; Wang, Chen; Kong, Miao; Tan, Yuxuan; Zhao, Li; Zhou, Wen; Shang, Dongdong; Zhu, Yamin; Hong, Yuan; Yu, Jianjun

doi:10.1109/ecoc52684.2021.9606010

Cited by 8 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The initial and final input symbols in the window lack the information of their neighbors, resulting in a smaller number of recovered output symbols [12]. Multi-symbol output equalizers draw attention to the research areas, previously proposed by [12], [25], [27].…”

Section: B Parallelization Of Recovered Symbolsmentioning

confidence: 99%

Parallelization of Recurrent Neural Network-Based Equalizer for Coherent Optical Systems via Knowledge Distillation

Srivallapanondh,

Freire,

Spinnler

et al. 2024

J. Lightwave Technol.

View full text Add to dashboard Cite

The recurrent neural network (RNN)-based equalizers, especially the bidirectional long-short-term memory (biL-STM) structure, have already been proven to outperform the feed-forward NNs in nonlinear mitigation in coherent optical systems. However, the recurrent connections still prevent the computation from being fully parallelizable. To circumvent the non-parallelizability of recurrent-based equalizers, we propose, for the first time, knowledge distillation (KD) to recast the biLSTM into a parallelizable feed-forward 1D-convolutional NN structure. In this work, we applied KD to the cross-architecture regression problem, which is still in its infancy. We highlight how the KD helps the student's learning from the teacher in the regression problem. Additionally, we provide a comparative study of the performance of the NN-based equalizers for both the teacher and the students with different NN architectures. The performance comparison was carried out in terms of the Q-factor, inference speed, and computational complexity. The equalization performance was evaluated using both simulated and experimental data. The 1D-CNN outperformed other NN types as a student model with respect to the Q-factor. The proposed 1D-CNN showed a significant reduction in the inference time compared to the biLSTM while maintaining comparable performance in the experimental data and experiencing only a slight degradation in the Q-factor in the simulated data.

show abstract

Section: B Parallelization Of Recovered Symbolsmentioning

confidence: 99%

Parallelization of Recurrent Neural Network-Based Equalizer for Coherent Optical Systems via Knowledge Distillation

Srivallapanondh,

Freire,

Spinnler

et al. 2024

J. Lightwave Technol.

View full text Add to dashboard Cite

show abstract

“…5. Comparison of different PAM4 equalization systems with reservoir computing (RC) [34], [76]- [78] and DSP [79]- [83] in terms or data rate and distance. Ch: channel; Sim: simulation; Exp: experiment.…”

Section: Data Rate-distance Product Comparison With Other Published Workmentioning

confidence: 99%

Multi-Wavelength Photonic Neuromorphic Computing for Intra and Inter-Channel Distortion Compensations in WDM Optical Communication Systems

Wang

Lima

Shastri

et al. 2023

IEEE J. Select. Topics Quantum Electron.

View full text Add to dashboard Cite

DSP (digital signal processing) has been widely applied in optical communication systems to mitigate various signal distortions and has become one of the key technologies that have sustained data traffic growth over the past decade. However, the strict energy budget of application-specific integrated circuit-based DSP chips has prevented the deployment of some powerful but computationally costly DSP algorithms in real applications. As a result, fiber nonlinearity-induced signal distortions impede fiber communications systems, especially in wavelength-division multiplexed (WDM) transmission systems.To solve these challenges in DSP, there has been a surge of interest in implementing neural networks-based signal processing using photonics hardware (i.e., photonic neural networks). Photonic neural networks promise to break performance limitations in electronics and gain advantages in bandwidth, latency, and power consumption in solving intellectual tasks that are unreachable by conventional digital electronic platforms. This work proposes a photonic recurrent neural network (RNN) capable of simultaneously resolving dispersion and both intra-and inter-channel fiber nonlinearities in multiple WDM channels in the photonic domain, for the first time to our best knowledge. Furthermore, our photonic RNN can directly process optical WDM signals in the photonic domain, avoiding prohibitive energy consumption and speed overhead in analog to digital converters (ADC). Our proposed photonic RNN is fully compatible with mature silicon photonic fabrications. We demonstrate in simulation that our photonic RNN can process multiple WDM channels simultaneously and achieve a reduced bit error rate compared to typical DSP algorithms for all WDM channels in a pulse-amplitude modulation 4-level (PAM4) transmission system, thanks to its unique capability to address inter-channel fiber nonlinearities. In addition to signal quality performance, the proposed system also promises to significantly reduce the power consumption and the latency compared to the state-of-the-art DSP chips, according to our power and latency analysis.

show abstract

“…Beyond TD-FNNs, using NN which inherently includes memory, such as recurrent NN (RNN) in various flavors, has been considered. Reports in literature include conventional RNNs [9][10], gated recurrent units (GRUs) [11], and long-short-term memory (LSTMs) [12]. All structures (LSTM shown in Fig.…”

Section: Neural-network Based Equalizers For Im/ddmentioning

confidence: 99%

Reservoir-computing and neural-network-based equalization for short reach communication

Ros

Ranzini

Osadchuk

et al. 2022

Optica Advanced Photonics Congress 2022

View full text Add to dashboard Cite

show abstract

Multi-Symbol Output Long Short-Term Memory Neural Network Equalizer For 200+ Gbps IM/DD System

Cited by 8 publications

References 13 publications

Parallelization of Recurrent Neural Network-Based Equalizer for Coherent Optical Systems via Knowledge Distillation

Parallelization of Recurrent Neural Network-Based Equalizer for Coherent Optical Systems via Knowledge Distillation

Multi-Wavelength Photonic Neuromorphic Computing for Intra and Inter-Channel Distortion Compensations in WDM Optical Communication Systems

Reservoir-computing and neural-network-based equalization for short reach communication

Contact Info

Product

Resources

About