公开(公告)号：US10902349B2

公开(公告)日：2021-01-26

申请号：US15629082

申请日：2017-06-21

Applicant: SRI International

Inventor： Shalini Ghosh ,  Patrick D. Lincoln ,  Bhaskar S. Ramamurthy

IPC: G06N20/00 ,  G06F11/30 ,  G06N7/00 ,  G06F40/40

Abstract: Methods and systems of using machine learning to create a trusted model that improves the operation of a computer system controller are provided herein. In some embodiments, a machine learning method includes training a model using input data, extracting the model, and determining whether the model satisfies the trust-related constraints. If the model does not satisfy the trust-related constraint, modifying at least one of: the model using one or more model repair algorithms, the input data using one or more data repair algorithms, or a reward function of the model using one or more reward repair algorithms, and re-training the model using at least one of the modified model, the modified input data, or the modified reward function. If the model satisfies the trust-related constraints, providing the model as a trusted model that enables a computer system controller to perform system actions within predetermined guarantees.

公开(公告)号：US11651227B2

公开(公告)日：2023-05-16

申请号：US16226286

申请日：2018-12-19

Applicant: SRI International

Inventor： Shalini Ghosh ,  Patrick Lincoln ,  Ashish Tiwari ,  Susmit Jha

IPC: G06N3/08 ,  G06N3/04 ,  G06N3/084

CPC classification number: G06N3/084 ,  G06N3/0454

Abstract: In general, the disclosure describes techniques for facilitating trust in neural networks using a trusted neural network system. For example, described herein are multi-headed, trusted neural network systems that can be trained to satisfy one or more constraints as part of the training process, where such constraints may take the form of one or more logical rules and cause the objective function of at least one the heads of the trusted neural network system to steer, during machine learning model training, the overall objective function for the system toward an optimal solution that satisfies the constraints. The constraints may be non-temporal, temporal, or a combination of non-temporal and temporal. The constraints may be directly compiled to a neural network or otherwise used to train the machine learning model.

公开(公告)号：US20170364831A1

公开(公告)日：2017-12-21

申请号：US15629082

申请日：2017-06-21

Applicant: SRI International

Inventor： Shalini Ghosh ,  Patrick D. Lincoln ,  Bhaskar S. Ramamurthy

IPC: G06N99/00 ,  G06F17/28

Abstract: Methods and systems of using machine learning to create a trusted model that improves the operation of a computer system controller are provided herein. In some embodiments, a machine learning method includes training a model using input data, extracting the model, and determining whether the model satisfies the trust-related constraints. If the model does not satisfy the trust-related constraint, modifying at least one of: the model using one or more model repair algorithms, the input data using one or more data repair algorithms, or a reward function of the model using one or more reward repair algorithms, and re-training the model using at least one of the modified model, the modified input data, or the modified reward function. If the model satisfies the trust-related constraints, providing the model as a trusted model that enables a computer system controller to perform system actions within predetermined guarantees.