US Patent Application 18349902. TRANSFER LEARNING BASED ON CROSS-DOMAIN HOMOPHILY INFLUENCES simplified abstract
Jump to navigation
Jump to search
Contents
TRANSFER LEARNING BASED ON CROSS-DOMAIN HOMOPHILY INFLUENCES
Organization Name
INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventor(s)
Craig M. Trim of Glendale CA (US)
Aaron K. Baughman of Research Triangle Park NC (US)
Garfield W. Vaughn of Southbury CT (US)
Micah Forster of Austin TX (US)
TRANSFER LEARNING BASED ON CROSS-DOMAIN HOMOPHILY INFLUENCES - A simplified explanation of the abstract
This abstract first appeared for US patent application 18349902 titled 'TRANSFER LEARNING BASED ON CROSS-DOMAIN HOMOPHILY INFLUENCES
Simplified Explanation
The patent application describes methods, computer program products, and systems related to deep transfer learning networks.
- The methods involve generating multiple deep transfer learning networks.
- The methods also involve encoding one or more transfer layers.
- These techniques aim to improve the efficiency and effectiveness of transfer learning in computer systems.
Original Abstract Submitted
Methods, computer program products, and systems are presented. The methods can include, for instance: generating a plurality of deep transfer learning networks. Further, the methods can include, for instance: encoding one or more transfer layers.