Invention Grant
- Patent Title: Continual learning of artificial intelligence systems based on bi-level optimization
-
Application No.: US16697259Application Date: 2019-11-27
-
Publication No.: US11544558B2Publication Date: 2023-01-03
- Inventor: Ammar Shaker , Francesco Alesiani , Xiao He
- Applicant: NEC Laboratories Europe GmbH
- Applicant Address: DE Heidelberg
- Assignee: NEC Laboratories Europe GmbH
- Current Assignee: NEC Laboratories Europe GmbH
- Current Assignee Address: DE Heidelberg
- Agency: Leydig, Voit & Mayer, Ltd.
- Main IPC: G06N3/04
- IPC: G06N3/04 ; G06N3/08

Abstract:
A method of continual learning in an artificial intelligence system through bi-level optimization includes providing a stored data sample of a current task and providing a neural network subdivided into two parts including a parameter part and a hyper-parameter part. The method further includes performing bi-level optimization by separately training the two parts of the neural network. The neural network has been trained, prior to the bi-level optimization, on data samples of previous tasks.
Public/Granted literature
- US20210064989A1 CONTINUAL LEARNING OF ARTIFICIAL INTELLIGENCE SYSTEMS BASED ON BI-LEVEL OPTIMIZATION Public/Granted day:2021-03-04
Information query