Invention Grant
- Patent Title: Training ensemble models to improve performance in the presence of unreliable base classifiers
-
Application No.: US16889644Application Date: 2020-06-01
-
Publication No.: US11803780B2Publication Date: 2023-10-31
- Inventor: Yongjune Kim , Yuval Cassuto
- Applicant: Western Digital Technologies, Inc.
- Applicant Address: US CA San Jose
- Assignee: Western Digital Technologies, Inc.
- Current Assignee: Western Digital Technologies, Inc.
- Current Assignee Address: US CA San Jose
- Agency: PATTERSON + SHERIDAN, LLP
- Agent Steven H. VerSteeg
- Main IPC: G06N20/20
- IPC: G06N20/20 ; G06F16/28 ; G06N5/01 ; G06N7/01
Abstract:
A system and method for training base classifiers in a boosting algorithm includes optimally training base classifiers considering an unreliability model, and then using a scheme with an aggregator decoder that reverse-flips inputs using inter-classifier redundancy introduced in training.
Public/Granted literature
- US20210097446A1 Training Ensemble Models To Improve Performance In The Presence Of Unreliable Base Classifiers Public/Granted day:2021-04-01
Information query
