US 11,836,463 B2
Method and apparatus with neural network processing
Minje Kim, Hwaseong-si (KR); and Soonwan Kwon, Yongin-si (KR)
Assigned to Samsung Electronics Co., Ltd., Suwon-si (KR)
Filed by Samsung Electronics Co., Ltd., Suwon-si (KR)
Filed on Nov. 30, 2020, as Appl. No. 17/106,266.
Claims priority of application No. 10-2020-0089166 (KR), filed on Jul. 17, 2020.
Prior Publication US 2022/0019408 A1, Jan. 20, 2022
Int. Cl. G06F 7/544 (2006.01); G06G 7/16 (2006.01); G06F 9/30 (2018.01); G06F 7/57 (2006.01); G06N 3/063 (2023.01)
CPC G06F 7/5443 (2013.01) [G06F 7/57 (2013.01); G06F 9/3001 (2013.01); G06G 7/16 (2013.01); G06N 3/063 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A neural network device comprising:
a shift register circuit comprising registers configured to, in each cycle of plural cycles, transfer stored data to a next register and store new data received from a previous register;
a control circuit configured to sequentially input data of input activations included in an input feature map into the shift register circuit in a preset order; and
a processing circuit, comprising crossbar array groups that receive the input activations from at least one of the registers and perform a multiply-accumulate (MAC) operation with respect to the received input activation and weights, configured to select at least some of operation results output from the crossbar array groups at a preset number of cycles to be converted and accumulate and add the at least some operation results using a result of the converted to obtain an output activation in an output feature map.