US 12,321,842 B2
Electronic apparatus and method for controlling thereof
Jinsu Yeo, Suwon-si (KR); Youngyoon Lee, Suwon-si (KR); Youngcheon You, Suwon-si (KR); and Jaechool Lee, Suwon-si (KR)
Assigned to SAMSUNG ELECTRONICS CO., LTD., Suwon-si (KR)
Filed by SAMSUNG ELECTRONICS CO., LTD., Suwon-si (KR)
Filed on Oct. 19, 2021, as Appl. No. 17/505,259.
Application 17/505,259 is a continuation of application No. PCT/KR2021/001752, filed on Feb. 9, 2021.
Claims priority of application No. 10-2020-0055341 (KR), filed on May 8, 2020.
Prior Publication US 2022/0036152 A1, Feb. 3, 2022
Int. Cl. G06N 3/04 (2023.01); G06F 11/34 (2006.01); G06N 3/044 (2023.01); G06N 3/045 (2023.01); G06N 3/0464 (2023.01); G06N 3/0495 (2023.01); G06N 3/08 (2023.01); G06N 3/082 (2023.01); G06N 3/09 (2023.01); G06N 3/0985 (2023.01); H03M 7/30 (2006.01)
CPC G06N 3/04 (2013.01) [G06F 11/3409 (2013.01); H03M 7/702 (2013.01); G06N 3/044 (2023.01); G06N 3/045 (2023.01); G06N 3/0464 (2023.01); G06N 3/0495 (2023.01); G06N 3/08 (2013.01); G06N 3/082 (2013.01); G06N 3/09 (2023.01); G06N 3/0985 (2023.01); H03M 7/3059 (2013.01); H03M 7/70 (2013.01)] 15 Claims
OG exemplary drawing
 
1. A method for controlling an electronic apparatus, the method comprising:
receiving target data to be input as an input value of an operation;
selecting a generic-purpose artificial intelligence model;
generating a compressed artificial intelligence model based on the selected generic-purpose artificial intelligence model, wherein the generating of the compressed artificial intelligence model comprises compressing the selected generic-purpose artificial intelligence model using a low rank approximation algorithm by applying a singular value decomposition (SVD) algorithm for one matrix, and training the compressed artificial intelligence model;
generating a dedicated artificial intelligence model based on the compressed artificial intelligence model;
acquiring output data by performing the operation using the dedicated artificial intelligence model; and
providing the output data through an output interface,
wherein the generating of the compressed artificial intelligence model further comprises:
acquiring a rank of the SVD algorithm based on a compression rate,
compressing and training the selected generic-purpose artificial intelligence model based on the acquired rank and converting the compressed artificial intelligence model into a converted compressed artificial intelligence model,
determining a performance of the converted compressed artificial intelligence model based on a predetermined first threshold value, and
based on the performance of the converted compressed artificial intelligence model being lower than the predetermined first threshold value, generating the dedicated artificial intelligence model.