Invention Grant
- Patent Title: Deep learning bias detection in text
-
Application No.: US15445059Application Date: 2017-02-28
-
Publication No.: US10282414B2Publication Date: 2019-05-07
- Inventor: Hugo Mike Latapie , Enzo Fenoglio , Guillaume Sauvage De Saint Marc , Monique Jeanne Morrow , Manikandan Kesavan
- Applicant: Cisco Technology, Inc.
- Applicant Address: US CA San Jose
- Assignee: Cisco Technology, Inc.
- Current Assignee: Cisco Technology, Inc.
- Current Assignee Address: US CA San Jose
- Agency: Behmke Innovation Group LLC
- Agent James Behmke; Stephen D. LeBarron
- Main IPC: G06F3/0484
- IPC: G06F3/0484 ; G06F17/27 ; G06N3/08
Abstract:
In one embodiment, a method includes obtaining text from a user, applying the text to a deep learning neural network to generate a plurality of bias coordinates defining a point in an embedded space, and, in response to determining that at least one of the plurality of bias coordinates exceeds a threshold, providing an indication of bias to the user.
Public/Granted literature
- US20180246873A1 Deep Learning Bias Detection in Text Public/Granted day:2018-08-30
Information query
