Deep Neural Network a Posteriori Probability Detector for Two-Dimensional Magnetic Recording

• Published in: IEEE transactions on magnetics Vol. 56; no. 6; pp. 1 - 12
• Main Authors: Shen, Jinlu, Aboutaleb, Ahmed, Sivakumar, Krishnamoorthy, Belzer, Benjamin J., Chan, Kheong Sann, James, Ashish
• Format: Journal Article
• Language: English
• Published: New York IEEE 01-06-2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Artificial neural networks; Bit error rate; Channel detection; Channels; Computer architecture; Computer simulation; convolutional neural network (CNN); Decoding; deep learning; Density; Detectors; Equalizers; Error analysis; grain-flipping-probability (GFP) model; Iterative methods; long short-term memory (LSTM); Magnetic recording; Magnetism; Media; Neural networks; Noise prediction; recurrent neural network; Statistical analysis; Two dimensional displays; two-dimensional magnetic recording (TDMR); Viterbi algorithm detectors
• DOI: 10.1109/TMAG.2020.2985636
• EISSN: 1941-0069
• ISSN: 0018-9464

In two-dimensional magnetic recording (TDMR) channels, intersymbol interference (within and between tracks) and pattern-dependent media noise are impediments to reaching higher areal density. We propose a novel deep neural network (DNN)-based a posteriori probability (APP) detection system with parallel multi-track detection for TDMR channels. The proposed DNN-based APP detector replaces the trellis-based Bahl-Cocke-Jelinek-Raviv (BCJR) or Viterbi algorithm and pattern-dependent noise prediction (PDNP) in a typical TDMR scenario, in which it directly outputs log-likelihood ratios of the coded bits and iteratively exchanges them with a subsequent channel decoder to minimize bit error rate (BER). We investigate three DNN architectures-fully connected DNN, convolutional neural network (CNN), and long short-term memory (LSTM) network. The DNN's complexity is limited by employing linear partial response (PR) equalizer pre-processing. The best performing DNN architecture, CNN, is selected for iterative decoding with a channel decoder. Simulation results on a grain-flipping-probability (GFP) media model show that all three DNN architectures yield significant BER reductions over a recently proposed 2D-PDNP system and a previously proposed local area influence probabilistic (LAIP)-BCJR system. On a GFP model with 18 nm track pitch and 11.4 Teragrains/in 2 , the CNN detection system achieves an information areal density of 3.08 Terabits/in 2 , i.e., a 21.72% density gain over a standard BCJR-based 1D-PDNP; the CNN-based system also has <inline-formula> <tex-math notation="LaTeX">3\times </tex-math></inline-formula> the throughput of 1D-PDNP, yet requires only 1/10th the computer run time.