Journal
IEEE COMMUNICATIONS LETTERS
Volume 25, Issue 12, Pages 3883-3887Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LCOMM.2021.3112908
Keywords
Threshold voltage; Ash; Detection algorithms; Convolutional neural networks; Training; Voltage measurement; Quantization (signal); NAND flash memory; convolutional neural network; read voltages; detection
Categories
Funding
- NSF of China [62071131, 61771149, U2001203, 61871136]
- Open Research Fund of the State Key Laboratory of Integrated Services Networks [ISN22-23]
- NSF of Guangdong Province [2019A1515011465]
- Guangdong Innovative Research Team Program [2014ZT05G157]
Ask authors/readers for more resources
The paper proposes a CNN-based detection algorithm for threshold voltage distribution detection in MLC flash memory, along with a CNN-aided read voltage design scheme to optimize detection performance. Simulation results show that the algorithm can achieve performance approaching that of the optimal detection algorithm.
With the increase of program/erase (PE) cycles and retention time, it is difficult to predict the threshold-voltage distributions for detection in NAND flash memory. To accurately acquire the log-likelihood ratios (LLRs) without the knowledge of threshold-voltage distributions, a convolutional neural network (CNN)-based detection algorithm is proposed for the multi-level-cell (MLC) flash memory. The CNN-based detection algorithm employs the trained CNN to accurately calculate the LLRs for each threshold-voltage region. Furthermore, we develop a CNN-aided read-voltage design scheme to optimize the read voltages by maximizing the mutual information between the coded bits and their corresponding LLRs. Exploiting the proposed scheme, we first design three hard-decision read voltages, and then formulate more soft-decision read voltages to further improve the detection performance. Simulation results demonstrate that the CNN-based detection algorithm can achieve performance approaching that of the optimal detection algorithm.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available