US 12,248,864 B2
Method of training artificial neural network and method of evaluating pronunciation using the method
Seung Won Park, Gyeonggi-do (KR); Jong Mi Lee, Gyeonggi-do (KR); and Kang Wook Kim, Seoul (KR)
Assigned to MINDS LAB INC., Daejeon (KR)
Filed by MINDS LAB INC., Daejeon (KR)
Filed on Oct. 13, 2021, as Appl. No. 17/500,645.
Application 17/500,645 is a continuation of application No. PCT/KR2021/010130, filed on Aug. 3, 2021.
Claims priority of application No. 10-2020-0165065 (KR), filed on Nov. 30, 2020.
Prior Publication US 2022/0172025 A1, Jun. 2, 2022
Int. Cl. G06N 3/045 (2023.01)
CPC G06N 3/045 (2023.01) 7 Claims
OG exemplary drawing
 
1. A method of training an artificial neural network, the method comprising: generating first output data corresponding to first training input data, by using a first artificial neural network, wherein the first artificial neural network is trained based on a plurality of training data comprising a first feature and a second feature that has a correlation with the first feature and depends on the first feature; and the first artificial neural network is a neural network trained to generate output data corresponding to the first feature from input data; generating third output data corresponding to the first output data and second training output data, by using a second artificial neural network, wherein the second artificial neural network is a neural network trained to output a result of comparison between the first output data and the second training output data, and the second training output data includes data comprising the second feature of the first training input data; generating at least one weight correction value for training the first artificial neural network based on the third output data; and applying the at least one weight correction value to the first artificial neural network, wherein the least one weight correction value is determined by a method in which a scale factor applied to at least one gradient value.