Deep Transfer Learning-based Detection for Flash Memory Channels

TL;DR

A model-based deep TL (DTL) algorithm using moment alignment and an unsupervised domain adaptation (UDA)-based DTL algorithm using moment alignment, which can detect data without any labels are proposed, suitable for scenarios where the decoding of error-correcting code fails and no labels can be obtained.

Abstract

The NAND flash memory channel is corrupted by different types of noises, such as the data retention noise and the wear-out noise, which lead to unknown channel offset and make the flash memory channel non-stationary. In the literature, machine learning-based methods have been proposed for data detection for flash memory channels. However, these methods require a large number of training samples and labels to achieve a satisfactory performance, which is costly. Furthermore, with a large unknown channel offset, it may be impossible to obtain enough correct labels. In this paper, we reformulate the data detection for the flash memory channel as a transfer learning (TL) problem. We then propose a model-based deep TL (DTL) algorithm for flash memory channel detection. It can effectively reduce the training data size from $10^6$ samples to less than 104 samples. Moreover, we propose an unsupervised domain adaptation (UDA)-based DTL algorithm using moment alignment, which can detect data without any labels. Hence, it is suitable for scenarios where the decoding of error-correcting code fails and no labels can be obtained. Finally, a UDA-based threshold detector is proposed to eliminate the need for a neural network. Both the channel raw error rate analysis and simulation results demonstrate that the proposed DTL-based detection schemes can achieve near-optimal bit error rate (BER) performance with much less training data and/or without using any labels.

Figures (16)

• Figure 1: The initial threshold voltage distributions of MLC ($q=2$) NAND flash memory.
• Figure 2: The stacked RNN architecture for data detection.
• Figure 3: RBER performance of the optimum threshold detector and the RNN detector with different number of training samples at $N_{\text{PE}}=10^{3}$ and $T=10^{3}$ hours.
• Figure 4: Training process of model-based DTL (a) Pre-training (b) Finetuning (Retraining).
• Figure 5: Illustration of model-based DTL with weights reuse.