Learning device, inference device, learning method, and inference method

An inference device comprising:

• a memory;
• and
• one or more processors coupled to the memory and configured to:
• receive input data;
• perform an inference operation by inputting the input data to a neural network which includes:
• nodes equal in number to number of rows of a transformation matrix generated from learning data;
• a first output layer representing first estimation distribution according to values of the nodes;
• and
• a second output layer representing second estimation distribution decided according to product of the transformation matrix and the first estimation distribution;
• and
• output, as inference result, output of the second output layer.

A learning method comprising:

• generating, by a learning device, a transformation matrix from learning data in which feature quantities and target values are held in a corresponding manner;
• and
• learning, by the learning device, 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 first estimation distribution according to values of the nodes;
• and
• a second output layer representing second estimation distribution decided according to product of the transformation matrix and the first estimation distribution.