Refine
Document Type
- Article (1)
- Conference Proceeding (1)
Language
- English (2)
Keywords
- Channel estimation (2) (remove)
Institute
Error correction coding based on soft-input decoding can significantly improve the reliability of flash memories. Such soft-input decoding algorithms require reliability information about the state of the memory cell. This work proposes a channel model for soft-input decoding that considers the asymmetric error characteristic of multi-level cell (MLC) and triple-level cell (TLC) memories. Based on this model, an estimation method for the channel state information is devised which avoids additional pilot data for channel estimation. Furthermore, the proposed method supports page-wise read operations.
Non-volatile NAND flash memories store information as an electrical charge. Different read reference voltages are applied to read the data. However, the threshold voltage distributions vary due to aging effects like program erase cycling and data retention time. It is necessary to adapt the read reference voltages for different life-cycle conditions to minimize the error probability during readout. In the past, methods based on pilot data or high-resolution threshold voltage histograms were proposed to estimate the changes in voltage distributions. In this work, we propose a machine learning approach with neural networks to estimate the read reference voltages. The proposed method utilizes sparse histogram data for the threshold voltage distributions. For reading the information from triple-level cell (TLC) memories, several read reference voltages are applied in sequence. We consider two histogram resolutions. The simplest histogram consists of the zero-and-one ratios for the hard decision read operation, whereas a higher resolution is obtained by considering the quantization levels for soft-input decoding. This approach does not require pilot data for the voltage adaptation. Furthermore, only a few measurements of extreme points of the threshold voltage distributions are required as training data. Measurements with different conditions verify the proposed approach. The resulting neural networks perform well under other life-cycle conditions.