US 12,230,319 B2
Determination of a bias voltage to apply to one or more memory cells in a neural network
Hieu Van Tran, San Jose, CA (US)
Assigned to SILICON STORAGE TECHNOLOGY, INC., San Jose, CA (US)
Filed by Silicon Storage Technology, Inc., San Jose, CA (US)
Filed on Jan. 26, 2022, as Appl. No. 17/585,452.
Claims priority of provisional application 63/279,028, filed on Nov. 12, 2021.
Prior Publication US 2023/0154528 A1, May 18, 2023
Int. Cl. G11C 11/54 (2006.01); G06N 3/063 (2023.01); G11C 16/04 (2006.01); G11C 16/10 (2006.01); G11C 16/24 (2006.01); G11C 16/26 (2006.01); H10B 41/30 (2023.01)
CPC G11C 11/54 (2013.01) [G06N 3/063 (2013.01); G11C 16/0425 (2013.01); G11C 16/10 (2013.01); G11C 16/24 (2013.01); G11C 16/26 (2013.01); H10B 41/30 (2023.02)] 15 Claims
OG exemplary drawing
 
1. A method for a neural network, the method comprising:
sensing an operating temperature associated with a set of memory cells;
determining a bias in a lookup table based on the sensed operating temperature and whether it is desired to target for power consumption or performance, wherein the lookup table comprises the sensed operating temperature value correlated with a first bias value for use when targeting power consumption and a second bias value for use when targeting performance;
applying the determined bias to terminals of the set of memory cells; and
performing a read operation on the set of memory cells.