US 11,755,408 B2
Systems for estimating bit error rate (BER) of encoded data using neural networks
Fa-Long Luo, San Jose, CA (US); and Jaime Cummins, Bainbridge Island, WA (US)
Assigned to Micron Technology, Inc., Boise, ID (US)
Filed by Micron Technology, Inc., Boise, ID (US)
Filed on Oct. 7, 2021, as Appl. No. 17/496,703.
Prior Publication US 2023/0115877 A1, Apr. 13, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. H03M 13/27 (2006.01); H04L 27/34 (2006.01); H04L 1/00 (2006.01); H03M 13/25 (2006.01); G06F 11/10 (2006.01); G06N 3/045 (2023.01)
CPC G06F 11/1068 (2013.01) [G06N 3/045 (2023.01)] 21 Claims
OG exemplary drawing
 
13. A method comprising:
receiving, at a computing device that comprises a neural network, codewords encoded in accordance with an encoding technique having a coding rate and a bit error rate (BER);
determining, for the neural network, a set of weights that causes the neural network to estimate the BER of the codewords.