Invention Grant
- Patent Title: Systems and methods for training generative models using summary statistics and other constraints
-
Application No.: US17074364Application Date: 2020-10-19
-
Publication No.: US12008478B2Publication Date: 2024-06-11
- Inventor: Aaron M. Smith , Anton D. Loukianov , Charles K. Fisher , Jonathan R. Walsh
- Applicant: Unlearn.AI, Inc.
- Applicant Address: US CA San Francisco
- Assignee: Unlearn.AI, Inc.
- Current Assignee: Unlearn.AI, Inc.
- Current Assignee Address: US CA San Francisco
- Agency: KPPB LLP
- Main IPC: G06N20/00
- IPC: G06N20/00 ; G06F18/211 ; G06N3/088 ; G06N7/08
Abstract:
Systems and methods for training and utilizing constrained generative models in accordance with embodiments of the invention are illustrated. One embodiment includes a method for training a constrained generative model. The method includes steps for receiving a set of data samples from a first distribution, identifying a set of constraints from a second distribution, and training a generative model based on the set of data samples and the set of constraints.
Public/Granted literature
- US20210117842A1 Systems and Methods for Training Generative Models Using Summary Statistics and Other Constraints Public/Granted day:2021-04-22
Information query
