Invention Grant
- Patent Title: Techniques for deriving and/or leveraging application-centric model metric
-
Application No.: US16887705Application Date: 2020-05-29
-
Publication No.: US11657334B2Publication Date: 2023-05-23
- Inventor: Arnold Boedihardjo , Adam Estrada , Andrew Jenkins , Nathan Clement , Alan Schoen
- Applicant: Radiant Analytic Solutions Inc.
- Applicant Address: US VA Herndon
- Assignee: MAXAR MISSION SOLUTIONS INC.
- Current Assignee: MAXAR MISSION SOLUTIONS INC.
- Current Assignee Address: US CO Westminster
- Agency: Nixon & Vanderhye PC
- Main IPC: G06N20/20
- IPC: G06N20/20 ; G06N20/00 ; G06N5/04 ; G06F18/21 ; G06F18/214 ; G06V10/75 ; G06V10/764 ; G06V10/77 ; G06V40/16

Abstract:
Techniques for recommending a prediction model from among a number of different prediction models are provided. Each of these prediction models has been trained based on a respective training data set, and each performs in accordance with a respective theoretical performance manifold. An indication of a region definable in relation to the theoretical performance manifolds of the different prediction models is received as input. For each of the different prediction models, the indication of the region is linked to features parameterizing the respective performance manifold; and one or more portions of the respective performance manifold is/are identified based on the features determined by the linking, the portion(s) having a volume and a shape that collectively denote an expected performance of the respective model for the input. The expected performance of the prediction models for the input is compared. Based on the comparison, one or more of the models is/are suggested.
Public/Granted literature
- US20200380308A1 TECHNIQUES FOR DERIVING AND/OR LEVERAGING APPLICATION-CENTRIC MODEL METRIC Public/Granted day:2020-12-03
Information query