US 12,249,125 B2
Learning apparatus, method and computer readable medium
Tomohiro Nakai, Kawasaki (JP)
Assigned to KABUSHIKI KAISHA TOSHIBA, Tokyo (JP)
Filed by KABUSHIKI KAISHA TOSHIBA, Tokyo (JP)
Filed on Feb. 18, 2022, as Appl. No. 17/651,653.
Claims priority of application No. 2021-091243 (JP), filed on May 31, 2021.
Prior Publication US 2022/0383622 A1, Dec. 1, 2022
Int. Cl. G06V 10/774 (2022.01); G06N 3/08 (2023.01); G06T 7/00 (2017.01); G06V 10/764 (2022.01)
CPC G06V 10/774 (2022.01) [G06N 3/08 (2013.01); G06T 7/0002 (2013.01); G06V 10/764 (2022.01)] 15 Claims
OG exemplary drawing
 
1. A learning apparatus comprising a processor configured to:
acquire first training data;
input the first training data to a model, and generate a plurality of estimation vectors that are a processing result of the model;
generate an estimation distribution from the estimation vectors;
calculate a distribution loss between the estimation distribution and a target distribution that is a target in an inference using the model;
calculate an entropy loss from the estimation vectors; and
update parameters of the model, based on the entropy loss and the distribution loss.