Overestimation Trap of Artificial Neural Network: Learning the Rule of PRBS

Shu, Liang; Li, Jianqiang; Wan, Zhiquan; Zhang, Wenjia; Fu, Songnian; Xu, Kun

doi:10.1109/ecoc.2018.8535327

Cited by 16 publications

(12 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 3 b shows BER is reduced with increasing input symbol. The smooth BER change, without large-scale jump between any adjacent two points, also indicates that NNE in our experiment does not obtain over-estimation gain thanks to the use of randomization process, since that over-estimation problem for NNE will lead to stair-like curve of BER versus input symbol number [ 27 ]. Moreover, design space for NNE also includes activation function and layer number, which influence equalization performance.…”

Section: Experiments and Resultsmentioning

confidence: 99%

Compressed Nonlinear Equalizers for 112-Gbps Optical Interconnects: Efficiency and Stability

Zhang

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

Low-complexity nonlinear equalization is critical for reliable high-speed short-reach optical interconnects. In this paper, we compare the complexity, efficiency and stability performance of pruned Volterra series-based equalization (VE) and neural network-based equalization (NNE) for 112 Gbps vertical cavity surface emitting laser (VCSEL) enabled optical interconnects. The design space of nonlinear equalizers and their pruning algorithms are carefully investigated to reveal fundamental reasons of powerful nonlinear compensation capability and restriction factors of efficiency and stability. The experimental results show that NNE has more than one order of magnitude bit error rate (BER) advantage over VE at the same computation complexity and pruned NNE has around 50% lower computation complexity compared to VE at the same BER level. Moreover, VE shows serious performance instability due to its intricate structure when communication channel conditions become tough. Moreover, pruned VE presents more consistent equalization performance within varying bias values than NNE.

show abstract

Section: Experiments and Resultsmentioning

confidence: 99%

Compressed Nonlinear Equalizers for 112-Gbps Optical Interconnects: Efficiency and Stability

Zhang

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…Validation set and test set are also adopted to prevent the over-fitting problem and evaluate the performance of MPANN, respectively. During the training and test process of MPANN, the order of all samples in every batch is randomized to avoid the memory effect for PRBS sequence 36 . This method has been validated in VLC system in Ref.…”

Section: Cap and Mpann Equalizermentioning

confidence: 99%

Demonstration of a low-complexity memory-polynomial-aided neural network equalizer for CAP visible-light communication with superluminescent diode

Holguín‐Lerma

Mao

et al. 2020

Opto-Electronic Advances

View full text Add to dashboard Cite

Visible-light communication (VLC) stands as a promising component of the future communication network by providing high-capacity, low-latency, and high-security wireless communication. Superluminescent diode (SLD) is proposed as a new light emitter in the VLC system due to its properties of droop-free emission, high optical power density, and low speckle-noise. In this paper, we analyze a VLC system based on SLD, demonstrating effective implementation of carrierless amplitude and phase modulation (CAP). We create a low-complexity memory-polynomial-aided neural network (MPANN) to replace the traditional finite impulse response (FIR) post-equalization filters of CAP, leading to significant mitigation of the linear and nonlinear distortion of the VLC channel. The MPANN shows a gain in Q factor of up to 2.7 dB higher than other equalizers, and more than four times lower complexity than a standard deep neural network (DNN), hence, the proposed MPANN opens a pathway for the next generation of robust and efficient neural network equalizers in VLC. We experimentally demonstrate a proof-of-concept 2.95-Gbit/s transmission using MPANN-aided CAP with 16-quadrature amplitude modulation (16-QAM) through a 30-cm channel based on the 442-nm blue SLD emitter.

show abstract

“…Nowadays, neural network is one of the most popular spots for academic researches and industry applications. In optical transmissions, neural networks have been applied to compensate some complicated distortions [13][14][15]. In short-reach optical interconnects, the distortion models are almost certain.…”

Section: Introductionmentioning

confidence: 99%

Adaptive moment estimation for polynomial nonlinear equalizer in PAM8-based optical interconnects

Zhou¹,

Wang²,

Wei³

et al. 2019

Opt. Express

View full text Add to dashboard Cite

Adaptive moment estimation (Adam) is a popular optimization method to estimate large-scale parameters in neural networks. This paper proposes the first use of Adam algorithm to fast and stably converge large-scale tap coefficients of polynomial nonlinear equalizer (PNLE) for 129-Gbit/s PAM8-based optical interconnects. PNLE is one of simplified Volterra nonlinear equalizer for making a trade-off between complexity and performance. Different from serial least-mean square (LMS) adaptive algorithm, Adam algorithm is a parallel processing algorithm, which can obtain globally optimal tap coefficients without being trapped in locally optimal tap coefficients. Timing error is one of the main obstacles to the PAM systems with high baud rate and high modulation order. Owing to parallel processing and global optimization, Adam algorithm has much better performance on resisting the timing error, which can achieve faster, more-stable and lower-MSE convergence compared to LMS adaptive algorithm. In conclusion, Adam algorithm shows great potential for converging the tap coefficients of PNLE in PAM8-based optical interconnects.

show abstract

Overestimation Trap of Artificial Neural Network: Learning the Rule of PRBS

Cited by 16 publications

References 2 publications

Compressed Nonlinear Equalizers for 112-Gbps Optical Interconnects: Efficiency and Stability

Compressed Nonlinear Equalizers for 112-Gbps Optical Interconnects: Efficiency and Stability

Demonstration of a low-complexity memory-polynomial-aided neural network equalizer for CAP visible-light communication with superluminescent diode

Adaptive moment estimation for polynomial nonlinear equalizer in PAM8-based optical interconnects

Contact Info

Product

Resources

About