US 11,790,232 B2
Method and apparatus with neural network data input and output control
Hyung-Dal Kwon, Hwaseong-si (KR)
Assigned to Samsung Electronics Co., Ltd., Suwon-si (KR)
Filed by SAMSUNG ELECTRONICS CO., LTD., Suwon-si (KR)
Filed on Jan. 11, 2023, as Appl. No. 18/95,674.
Application 18/095,674 is a continuation of application No. 16/900,007, filed on Jun. 12, 2020, granted, now 11,580,393.
Claims priority of application No. 10-2019-0176097 (KR), filed on Dec. 27, 2019.
Prior Publication US 2023/0162034 A1, May 25, 2023
Int. Cl. G06N 3/08 (2023.01); G06N 3/04 (2023.01); H03M 7/30 (2006.01)
CPC G06N 3/08 (2013.01) [G06N 3/04 (2013.01); H03M 7/30 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A neural network deep learning data control apparatus comprising:
a memory;
an encoding circuit configured to
receive a data sequence,
generate a compressed data sequence by compressing consecutive bits having the same bit value in a bit string of the data sequence are compressed into a single bit of the compressed data sequence,
generate a data discrimination sequence discriminating a data repetition bit and an invalid bit in a bit string of the compressed data sequence, and
write the compressed data sequence and the data discrimination sequence to the memory; and
a decoding circuit configured to
read the compressed data sequence and the data discrimination sequence from the memory, and
determine a bit in the bit string of the compressed data sequence set for transmission to a neural network circuit, based on the data discrimination sequence.