Invention Application
- Patent Title: MODULARIZED ARCHITECTURE OPTIMIZATION FOR SEMI-SUPERVISED INCREMENTAL LEARNING
-
Application No.: US18520800Application Date: 2023-11-28
-
Publication No.: US20240403649A1Publication Date: 2024-12-05
- Inventor: Han-Pang Chiu , Yi Yao , Zachary Seymour , Alex Krasner , Bradley J. Clymer , Michael A. Cogswell , Cecile Eliane Jeannine Mackay , Alex C. Tozzo , Tixiao Shan , Philip Miller , Chuanyong Gan , Glenn A. Murray , Richard Louis Ferranti , Uma Rajendran , Supun Samarasekera , Rakesh Kumar , James Smith
- Applicant: SRI International
- Applicant Address: US CA Menlo Park
- Assignee: SRI International
- Current Assignee: SRI International
- Current Assignee Address: US CA Menlo Park
- Main IPC: G06N3/0895
- IPC: G06N3/0895

Abstract:
In an example, a system includes processing circuitry in communication with storage media. The processing circuitry is configured to execute a machine learning system including at least a first module, a second module and a third module. The machine learning system is configured to train one or more machine learning models. The first module is configured to generate augmented input data based on the streaming input data. The second module includes a machine learning model configured to perform a specific task based at least in part on the augmented input data. The third module configured to adapt a network architecture of the one or more machine learning models based on changes in the streaming input data.
Information query