Invention Grant
- Patent Title: Automated explanation of machine learning predictions using classification score targeting
-
Application No.: US16690169Application Date: 2019-11-21
-
Publication No.: US11315342B2Publication Date: 2022-04-26
- Inventor: Yoel Shoshan , Vadim Ratner
- Applicant: International Business Machines Corporation
- Applicant Address: US NY Armonk
- Assignee: International Business Machines Corporation
- Current Assignee: International Business Machines Corporation
- Current Assignee Address: US NY Armonk
- Agency: Dvir Gassner
- Main IPC: G06V10/75
- IPC: G06V10/75 ; G06K9/62 ; G06N20/00 ; G06N5/04

Abstract:
Automated explanation of machine learning predictions, by: Obtaining an input, a machine learning model, and a classification score produced by application of the machine learning model to the input. Optimizing iterative application of the machine learning model to perturbations of the input, wherein a target of said optimizing is at least a predefined non-zero classification score. Generating, based on one of the perturbations which achieved the predefined non-zero classification score, an explanation to the classification score produced by the application of the machine learning model to the input.
Public/Granted literature
- US20210158075A1 Automated Explanation of Machine Learning Predictions Using Classification Score Targeting Public/Granted day:2021-05-27
Information query