A method of learning and testing a modulation network that conceals the original data for the protection of personal information, and a learning device and a test device using this.

摘要

The present invention is a method of learning a modulation network that conceals original data for personal information protection, in which the learning device modulates the learning data input by the modulation network and converts the modulated learning data into a learning network. The stage of inputting and applying the network calculation to the modulated learning data by the learning network to generate the first characteristic information; the second by applying the network calculation to the input learning data by the learning network. The stage of generating characteristic information; and at least one of the error acquired by referring to the first and second characteristic information, the task specific output, and the error acquired by referring to the corresponding original correct answer. Provides a method that includes a step of learning a modulation network so as to minimize the error calculated by referring to the part and maximize the error calculated by referring to the training data and the modulated training data. ..