	US 12,354,014 B2
	Generation and discrimination training as a variable resolution game
James K. Baker, Maitland, FL (US)
Assigned to D5AI LLC, Maitland, FL (US)
Appl. No. 18/852,145
Filed by D5AI LLC, Maitland, FL (US)
PCT Filed Mar. 14, 2023, PCT No. PCT/US2023/064296 § 371(c)(1), (2) Date Sep. 27, 2024, PCT Pub. No. WO2023/192766, PCT Pub. Date Oct. 5, 2023.
Claims priority of provisional application 63/362,267, filed on Mar. 31, 2022.
Prior Publication US 2025/0103896 A1, Mar. 27, 2025
Int. Cl. G06N 3/045 (2023.01); G06N 3/094 (2023.01)

CPC G06N 3/094 (2023.01) [G06N 3/045 (2023.01)]

36 Claims

1. A method of training a generator and discriminator adversarially, the method comprising training, through machine learning, by a computer system, the generator and discriminator together in a multi-player, simulated game, wherein the simulated game comprises multiple rounds where, in each round, the discriminator determines whether a selected data item, presented to the discriminator, is from the generator or from a data source that is different from the generator, and wherein the training comprises:

training the discriminator to perform a first task, wherein the first task is whether the selected data item, presented to the discriminator, is from the generator or from the data source;

training the generator to generate data that the discriminator incorrectly determines is not from the generator; and

iteratively updating model parameters for the generator and for the discriminator,

wherein the training comprises:

in a first round of the simulated game:

updating, by the computer system, a current mixed strategy for the discriminator to thereby produce an updated mixed strategy for the discriminator;

obtaining, from the data source, a first data item based on the updated mixed strategy for the discriminator;

generating, by the generator, a second data item using a current mixed strategy for the generator;

inputting, by a computer system, a first selected data item to the discriminator, where the first selected data item is either the first data item or the second data item, wherein the computer system makes a first selection of either the first data item or the second data item, and wherein the discriminator does not know the first selection by the computer system;

determining, by the discriminator, whether the first selected data item was generated by the generator;

determining, by the computer system, whether the discriminator correctly determined whether the first selected data item was generated by the generator; and

assigning, by the computer system, a first payoff for the generator and for the discriminator based on whether the discriminator correctly determined whether the first selected data item was generated by the generator; and

in a second round of the simulated game:

updating, by the computer system, the current mixed strategy for the discriminator to thereby produce an updated mixed strategy for the generator;

obtaining, from the data source, a third data item based on the updated mixed strategy for the discriminator;

generating, by the generator, a fourth data item using the updated mixed strategy for the generator;

inputting, by a computer system, a second selected data item to the discriminator, where the second selected data item is either the third data item or the fourth data item, wherein the computer system makes a second selection of either the third data item or the fourth data item, and wherein the discriminator does not know the second selection by the computer system;

determining, by the discriminator, whether the second selected data item was generated by the generator;

determining, by the computer system, whether the discriminator correctly determined whether the second selected data item was generated by the generator; and

assigning, by the computer system, a second payoff for the generator and for the discriminator based on whether the discriminator correctly determined whether the second selected data item was generated by the generator.