Invention Grant
- Patent Title: Adaptive model insights visualization engine for complex machine learning models
-
Application No.: US16597336Application Date: 2019-10-09
-
Publication No.: US11544604B2Publication Date: 2023-01-03
- Inventor: Ashok Pancily Poothiyot , Vidit Bhatia , Matthew Colon
- Applicant: Adobe Inc.
- Applicant Address: US CA San Jose
- Assignee: Adobe Inc.
- Current Assignee: Adobe Inc.
- Current Assignee Address: US CA San Jose
- Agency: Keller Preece PLLC
- Main IPC: G06N5/04
- IPC: G06N5/04 ; G06N20/00 ; G06F8/20 ; G06F8/30 ; G06F8/34

Abstract:
The present disclosure relates to systems, methods, and non-transitory computer-readable media for utilizing a parameterized notebook to adaptively generate visualizations regarding machine-learning models. In particular, the disclosed systems can generate a parameterized notebook based on a user-defined visualization recipe and provide parameter values that correspond to the machine-learning model to the parameterized notebook. Upon execution of the user-defined visualization recipe via the parameterized notebook, the disclosed systems can extract visualization data corresponding to the machine-learning model from the parameterized notebook. In addition, the disclosed systems can generate visualizations based on the visualization data and provide the generated visualizations for display in a graphical user interface.
Public/Granted literature
- US20210110288A1 ADAPTIVE MODEL INSIGHTS VISUALIZATION ENGINE FOR COMPLEX MACHINE LEARNING MODELS Public/Granted day:2021-04-15
Information query