US 11,868,885 B2
Learning device, inference device, learning method, and inference method using a transformation matrix generated from learning data
Yuichi Kato, Kawasaki (JP); Kouta Nakata, Shinagawa (JP); Susumu Naito, Yokohama (JP); Yasunori Taguchi, Kawasaki (JP); and Kentaro Takagi, Yokohama (JP)
Assigned to KABUSHIKI KAISHA TOSHIBA, Minato-ku (JP)
Filed by KABUSHIKI KAISHA TOSHIBA, Minato-ku (JP)
Filed on Aug. 21, 2020, as Appl. No. 16/999,191.
Claims priority of application No. 2020-030794 (JP), filed on Feb. 26, 2020.
Prior Publication US 2021/0264259 A1, Aug. 26, 2021
Int. Cl. G06N 3/06 (2006.01); G06N 3/08 (2023.01); G06N 5/04 (2023.01); G06F 17/18 (2006.01); G06F 17/16 (2006.01); G06N 3/063 (2023.01)
CPC G06N 3/08 (2013.01) [G06F 17/16 (2013.01); G06F 17/18 (2013.01); G06N 3/063 (2013.01); G06N 5/04 (2013.01)] 9 Claims
OG exemplary drawing
 
1. A learning device comprising:
a memory; and
one or more processors coupled to the memory and configured to:
generate a transformation matrix from learning data in which feature quantities and target values are held in a corresponding manner; and
learn about parameters of a neural network which includes:
nodes equal in number to number of rows of the transformation matrix;
a first output layer representing a first estimation distribution according to values of the nodes; and
a second output layer representing a second estimation distribution decided according to a product of the transformation matrix and the first estimation distribution.