Invention Grant
- Patent Title: Incremental learning through state-based real-time adaptations in artificial intelligence systems
-
Application No.: US16197197Application Date: 2018-11-20
-
Publication No.: US11270206B2Publication Date: 2022-03-08
- Inventor: Eren Kursun
- Applicant: BANK OF AMERICA CORPORATION
- Applicant Address: US NC Charlotte
- Assignee: BANK OF AMERICA CORPORATION
- Current Assignee: BANK OF AMERICA CORPORATION
- Current Assignee Address: US NC Charlotte
- Agency: Moore & Van Allen PLLC
- Agent R. W. McCord Rayburn
- Main IPC: G06N3/08
- IPC: G06N3/08 ; G06N3/04

Abstract:
A system for reconfiguring neural network architecture responsive to a system state is provided. A controller for modifying a neural network learning engine is configured to monitor a data stream having a data pattern by comparing the data pattern to a trained data pattern; identify a change in the data pattern of the data stream; determine a state of the neural network learning engine, the state defining one or more neural network parameters for monitoring the data stream with the neural network learning engine; and in response to identifying the change in the data pattern and determining the state, reconfigure an architectural configuration of the neural network learning engine by modifying the one or more neural network parameters.
Public/Granted literature
- US20200160184A1 INCREMENTAL LEARNING THROUGH STATE-BASED REAL-TIME ADAPTATIONS IN ARTIFICAL INTELLIGENCE SYSTEMS Public/Granted day:2020-05-21
Information query