Invention Grant
- Patent Title: Generating representative unstructured data to test artificial intelligence services for bias
-
Application No.: US16157307Application Date: 2018-10-11
-
Publication No.: US10783068B2Publication Date: 2020-09-22
- Inventor: Biplav Srivastava , Francesca Rossi , Aleksandra Mojsilovic
- 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: McGinn IP Law Group, PLLC
- Agent Anthony Curro, Esq.
- Main IPC: G06F11/36
- IPC: G06F11/36 ; G06N5/04

Abstract:
A bias detection method, system, and computer program product to evaluate bias in an artificial intelligence service include selecting a bias context, the bias context having a bias specification associated with the bias context, generating test data for determining the bias in the artificial intelligence service based on the bias specification and the bias context, and testing the artificial intelligence service for the bias with the generated test data.
Public/Granted literature
- US20200117582A1 GENERATING REPRESENTATIVE UNSTRUCTURED DATA TO TEST ARTIFICIAL INTELLIGENCE SERVICES FOR BIAS Public/Granted day:2020-04-16
Information query