Nonlinear Equalization for TDMR Channels Using Neural Networks

Shen, Jinlu; Nangare, Nitin

doi:10.1109/ciss48834.2020.1570617082

Cited by 13 publications

(10 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Indeed, the high complexity of NN-based methods precludes practical implementation. For example, among the lowest complexity NN equalizers proposed by previous studies, the complexity of the MLP in [3] is about 6.6× the complexity of the 2D-LMMSE. To facilitate practical implementation, we propose four variants of a reduced complexity MLP (RC-MLP) architecture.…”

Section: Introductionmentioning

confidence: 99%

“…Both assumptions are not generally true in practice. Indeed, the readback waveforms suffer from non-linear impairments such as partial erasures, non-linear ISI/ITI, jitter noise, and asymmetry [2], [3]. To shorten the ISI/ITI, the typical data recovery system uses the 2D-linear minimum mean squared error (2D-LMMSE) equalizer followed the VA detector [2], [3].…”

Section: Introductionmentioning

confidence: 99%

“…Indeed, the readback waveforms suffer from non-linear impairments such as partial erasures, non-linear ISI/ITI, jitter noise, and asymmetry [2], [3]. To shorten the ISI/ITI, the typical data recovery system uses the 2D-linear minimum mean squared error (2D-LMMSE) equalizer followed the VA detector [2], [3]. The 2D-LMMSE is realized as a finite impulse response (FIR) filter for simplicity of implementation.…”

Section: Introductionmentioning

confidence: 99%

“…Compared with conventional equalizers and detection systems, neural networks (NNs) have been shown to compensate better for the non-linear impairments in high density magnetic recording channels with significant improvement in the overall system performance for 1DMR in [2], TDMR in [3], [5]- [7], and multilayer magnetic recording (MLMR) in [8].…”

Section: Introductionmentioning

confidence: 99%

“…In [8], Aboutaleb et al propose CNN-based systems for detection and equalization in MLMR channels with severe non-linear distortions. In [3], Shen and Nangare propose an NN equalizer followed by a VA, where the NN's parameters adapt to minimize the cross-entropy (CE). Therein, the authors show that adapting the equalizer's parameters to minimize the CE loss results lower detector BERs compared with MSE adaptation.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Reduced Complexity Neural Network Equalizers for Two-dimensional Magnetic Recording

Aboutaleb¹,

Nangare²

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Recent studies show promising performance gains achieved by non-linear equalization using neural networks (NNs) over traditional linear equalization in two-dimensional magnetic recording (TDMR) channels. But the examined neural network architectures entail much higher implementation complexities compared with the linear equalizer, which precludes practical implementation. For example, among the low complexity reported architectures, the multilayer perceptron (MLP) requires about 6.6 times increase in complexity over the linear equalizer. This paper investigates candidate reduced complexity neural network architectures for equalization over TDMR. We test the performance on readback signals measured over an actual hard disk drive with TDMR technology. Four variants of a reduced complexity MLP (RC-MLP) architecture are proposed. A proposed variant achieves the best balance between performance and complexity. This architecture consists of finite-impulse response filters, a nonlinear activation, and a hidden delay line. The complexity of the architecture is only 1.59 times the linear equalizer's complexity, while achieving most of the performance gains of the MLP.

show abstract

Section: Introductionmentioning

confidence: 99%