Minimization of compressed information is a well studied topic in image and audio processing. For images and audio, the degradation of the original data is suppressed to a constant level by restoring the data using the distribution and probability of occurrence.

Inspired by image compression theory, Fujitsu has pioneered a new mathematical theory that, for high-dimensional data with unknown distribution and probability, such as communication network access data and medical data, the dimensionality of the data is reduced by an auto-encoder neural network, and when the data is restored, the degradation between the original high-dimensional data and the restored data is kept to a constant value while the amount of information after the dimensionality reduction is minimized, enabling the characteristics of the original high-dimensional data to be accurately captured and the dimensionality to be reduced to a minimum.