US 11,861,504 B2
Apparatus for performing class incremental learning and method of operating the apparatus
Donghyun Lee, Seoul (KR); Euntae Choi, Seoul (KR); Kyungmi Lee, Cambridge, MA (US); and Kiyoung Choi, Seoul (KR)
Assigned to Samsung Electronics Co., Ltd., Suwon-si (KR); and Seoul National University R&DB Foundation, Seoul (KR)
Filed by Samsung Electronics Co., Ltd., Suwon-si (KR); and Seoul National University R&DB Foundation, Seoul (KR)
Filed on Mar. 26, 2020, as Appl. No. 16/830,480.
Claims priority of application No. 10-2019-0072422 (KR), filed on Jun. 18, 2019.
Prior Publication US 2020/0401900 A1, Dec. 24, 2020
Int. Cl. G06N 3/08 (2023.01); G06N 3/088 (2023.01); G06N 3/04 (2023.01)
CPC G06N 3/088 (2013.01) [G06N 3/04 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method of performing a class incremental learning in a neural network apparatus, the method comprising:
training an autoencoder using first input embeddings with respect to a first class group;
calculating a contribution value of each of parameters of the autoencoder and calculating a first plurality of representative values with respect to each of at least one first class included in the first class group in the training of the autoencoder;
retraining the autoencoder using second input embeddings with respect to a second class group; and
updating the contribution value of the each of the parameters, for the retraining, and calculating a second plurality of representative values with respect to each of at least one second class included in the second class group in the retraining the autoencoder based on a class of the first class group.