US Patent Application 18020588. MACHINE LEARNING SYSTEM, METHOD, INFERENCE APPARATUS AND COMPUTER-READABLE STORAGE MEDIUM simplified abstract
Contents
MACHINE LEARNING SYSTEM, METHOD, INFERENCE APPARATUS AND COMPUTER-READABLE STORAGE MEDIUM
Organization Name
Inventor(s)
MACHINE LEARNING SYSTEM, METHOD, INFERENCE APPARATUS AND COMPUTER-READABLE STORAGE MEDIUM - A simplified explanation of the abstract
This abstract first appeared for US patent application 18020588 titled 'MACHINE LEARNING SYSTEM, METHOD, INFERENCE APPARATUS AND COMPUTER-READABLE STORAGE MEDIUM
Simplified Explanation
The patent application describes a machine learning method that involves two learning phases.
- The first learning phase trains the parameters of a learning model using a dataset with correct answer labels.
- The second learning phase trains the parameters of a defender and an identifier using member and non-member data from different datasets.
- The second learning phase alternates between updating the parameters of the identifier based on input results and updating the parameters of the defender based on output results and identification results.
Original Abstract Submitted
A machine learning method including a first learning phase for training parameters θ of a learning model f by performing machine learning using a first dataset as a training data with a correct answer label; and a second learning phase for training parameters τ of a defender u and parameters ω of identifier h by performing machine learning using member data contained in the first dataset and non-member data contained in a second dataset. The second learning phase alternately performs, a first step for updating the parameters ω of the identifier h using the identification result when the first input result and the second input result are input to the identifier h; and a second step for updating the parameters τ of the defender u using the first output result, the second output result and the identification result.
