System and method for building artificial intelligence models or agents with immunity
AssigneeSouthern Methodist University
InventorsXihao Xie, Jia Zhang, Tsengdar J. Lee
Life of this patent
Estimating the term…
Abstract
A system and computer-implemented method for building an artificial intelligence model or agent with immunity includes providing a trusted dataset, a baseline model and a judge model, training a dynamic model from a new dataset, updating the new dataset with estimations from the judge model, refreshing the baseline model with the trained dynamic model, and augmenting the trusted dataset with the updated new dataset.
Claims40
A computer-implemented method for building an artificial intelligence model or agent, the method comprising:
- providing a trusted dataset, a baseline model and a judge model;
- training a dynamic model from a new dataset;
- updating the new dataset with estimations from the judge model;
- refreshing the baseline model with the trained dynamic model;
- and
- augmenting the trusted dataset with the updated new dataset.
A computerized system for building an artificial intelligence model or agent comprises:
- a trusted dataset;
- a baseline model;
- a judge model
- a dynamic model;
- and
- one or more processors communicably coupled to the trusted dataset, the baseline model, the judge model and the dynamic model, wherein the one or more processors train the dynamic model from a new dataset, update the new dataset with estimations from the judge model, refresh the baseline model with the trained dynamic model, and augment the trusted dataset with the updated new dataset.
Dependencies are inferred from the claim text.