Selbstabstimmung zur Entrauschung unter Verwendung mehrerer Schwellenexperten-Maschinenlernmodelle

Details

Veröffentlichungs-Nr.

EP4819142

Anmeldetag

29. Juli 2025

Veröffentlichung

7. Oktober 2026

Rechtsraum

EP

Abstract

Methods and devices for controlling a storage device including a non-volatile memory are provided, the methods including: reading (1321) a plurality of voltages from a target memory cell included in the non-volatile memory (220); obtaining (1322) a plurality of initial log-likelihood ratio (LLR) values by providing the plurality of voltages to an initial threshold model; generating (1323) at least one tuned model parameter based on the plurality of initial LLR values; tuning (1324) the initial threshold model based on the at least one tuned model parameter to obtain a tuned threshold model; obtaining (1325) a plurality of uncalibrated LLR values by providing the plurality of voltages to the tuned threshold model; calculating (1326) a calibration parameter based on the plurality of uncalibrated LLR values; modifying (1327) the tuned threshold model based on the calibration parameter to obtain calibrated tuned threshold model; obtaining (1328) a final predicted LLR value by providing at least one of the plurality of voltages to the calibrated tuned threshold model; and obtaining (1328) data based on the final predicted LLR values.

Anmelder

Firma

Samsung Electronics Co., Ltd.

Land

🇰🇷 Südkorea