Invention Grant
- Patent Title: Systems and methods of generating datasets from heterogeneous sources for machine learning
-
Application No.: US18151094Application Date: 2023-01-06
-
Publication No.: US11861510B2Publication Date: 2024-01-02
- Inventor: Douglas Hamilton , Michael O'Rourke , Xuyang Lin , Hyunsoo Jeong , William Dague , Tudor Morosan
- Applicant: Nasdaq, Inc.
- Applicant Address: US NY New York
- Assignee: NASDAQ, INC.
- Current Assignee: NASDAQ, INC.
- Current Assignee Address: US NY New York
- Agency: Nixon & Vanderhye P.C.
- Main IPC: G06F16/00
- IPC: G06F16/00 ; G06N5/022 ; G06N20/00 ; G06F16/25 ; G06F18/214 ; G06F18/2113 ; G06N5/01
Abstract:
A computer system is provided that is programmed to select feature sets from a large number of features. Features for a set are selected based on metagradient information returned from a machine learning process that has been performed on an earlier selected feature set. The process can iterate until a selected feature set converges or otherwise meets or exceeds a given threshold.
Public/Granted literature
- US20230142808A1 SYSTEMS AND METHODS OF GENERATING DATASETS FROM HETEROGENEOUS SOURCES FOR MACHINE LEARNING Public/Granted day:2023-05-11
Information query
