Sparse and Expandable Network for Google's Pathways
SEN offers a straightforward yet effective solution to the limitations of current lifelong multi-task learning methods. By addressing the challenges identified in the Pathways architecture, SEN provides a promising approach for developing AI systems capable of learning and adapting over time without sacrificing performance or efficiency.
Authors
- Charles X. Ling (ORCID: https://orcid.org/0000-0003-3797-1348)
- Ganyu Wang (ORCID: https://orcid.org/0000-0002-0573-1887)
- Boyu Wang (ORCID: https://orcid.org/0000-0002-7413-4162)
Institutions
- Western University (CA)
Publication Details
- Journal
- Frontiers in Big Data
- Published
- 2024-08-29
- DOI
- https://doi.org/10.3389/fdata.2024.1348030
- Primary Topic
- Domain Adaptation and Few-Shot Learning
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Natural Sciences and Engineering Research Council of Canada