Invention Grant
- Patent Title: Systems and methods for machine learning enhanced by human measurements
-
Application No.: US16842101Application Date: 2020-04-07
-
Publication No.: US11042785B2Publication Date: 2021-06-22
- Inventor: David Cox , Walter Scheirer , Samuel Anthony , Ken Nakayama
- Applicant: David Cox , Walter Scheirer , Samuel Anthony , Ken Nakayama
- Applicant Address: US MA Somerville; US MA Somerville; US MA Cambridge; US MA Cambridge
- Assignee: David Cox,Walter Scheirer,Samuel Anthony,Ken Nakayama
- Current Assignee: David Cox,Walter Scheirer,Samuel Anthony,Ken Nakayama
- Current Assignee Address: US MA Somerville; US MA Somerville; US MA Cambridge; US MA Cambridge
- Agency: Morgan, Lewis & Bockius LLP
- Main IPC: G06K9/00
- IPC: G06K9/00 ; G06K9/62

Abstract:
In various embodiments, training objects are classified by human annotators, psychometric data characterizing the annotation of the training objects is acquired, a human-weighted loss function based at least in part on the classification data and the psychometric data is computationally derived, and one or more features of a query object are computationally classifies based at least in part on the human-weighted loss function.
Public/Granted literature
- US20200242416A1 SYSTEMS AND METHODS FOR MACHINE LEARNING ENHANCED BY HUMAN MEASUREMENTS Public/Granted day:2020-07-30
Information query