Machine learning program, method, and device

A machine learning method, comprising:

• by a processor,
• specifying, among a plurality of points that are present within a predetermined distance from a first point in a latent space of an autoencoder, a second point that satisfies a predetermined relationship with the first point;
• and
• updating at least a parameter of a decoder of the autoencoder by optimization of an objective function including a regularization term to reduce a difference between the first point and the second point in the latent space.

A machine learning device, comprising:

• a memory;
• and
• a processor coupled to the memory, the processor being configured to execute processing, the processing including:
• specifying, among a plurality of points that are present within a predetermined distance from a first point in a latent space of an autoencoder, a second point that satisfies a predetermined relationship with the first point;
• and
• updating at least a parameter of a decoder of the autoencoder by optimization of an objective function including a regularization term to reduce a difference between the first point and the second point in the latent space.