US 12,136,257 B2
Learning device, learning method, and recording medium
Akinori Ebihara, Tokyo (JP); and Taiki Miyagawa, Tokyo (JP)
Assigned to NEC CORPORATION, Tokyo (JP)
Appl. No. 17/619,319
Filed by NEC Corporation, Tokyo (JP)
PCT Filed May 11, 2020, PCT No. PCT/JP2020/018889
§ 371(c)(1), (2) Date Dec. 15, 2021,
PCT Pub. No. WO2021/229663, PCT Pub. Date Nov. 18, 2021.
Prior Publication US 2022/0375204 A1, Nov. 24, 2022
Int. Cl. G06V 10/776 (2022.01); G06N 3/08 (2023.01); G06N 20/00 (2019.01); G06V 10/44 (2022.01); G06V 10/764 (2022.01); G06V 10/774 (2022.01); G06V 10/778 (2022.01); G06V 10/82 (2022.01); G06V 10/98 (2022.01); G06V 40/16 (2022.01)
CPC G06V 10/776 (2022.01) [G06N 3/08 (2013.01); G06N 20/00 (2019.01); G06V 10/454 (2022.01); G06V 10/764 (2022.01); G06V 10/7747 (2022.01); G06V 10/778 (2022.01); G06V 10/82 (2022.01); G06V 10/98 (2022.01); G06V 40/172 (2022.01)] 5 Claims
OG exemplary drawing
 
1. A learning device comprising:
a memory storing instructions; and
one or more processors connected to the memory and configured to execute the instructions to:
learn class classification of a classification target by using a loss function in which a loss is calculated to become smaller as a magnitude of a difference between a function value and a constant associated with a correct answer to the class classification of the classification target becomes smaller, wherein
the function value is obtained by inputting a log-likelihood ratio to a function having a finite value range, and
the log-likelihood ratio is a logarithm of a ratio between a likelihood that the classification target belongs to a first class and a likelihood that the classification target belongs to a second class;
acquire series data as the classification target;
classify the series data into the first class or the second class using the learned class classification in relation to the acquired series data; and
display a classification of the series data on a display.