Continual learning via inter-task synaptic mapping
Learning from streaming tasks leads a model to catastrophically erase unique experiences it absorbs from previous episodes. While regularization techniques such as LWF, SI, EWC have proven themselves as an effective avenue to overcome this issue by constraining important parameters of old tasks f...
Main Authors: | Mao, Fubing, Weng, Weiwei, Pratama, Mahardhika, Yee, Edward Yapp Kien |
---|---|
Other Authors: | School of Computer Science and Engineering |
Format: | Journal Article |
Language: | English |
Published: |
2022
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/160691 |
Similar Items
-
Cross-domain continual learning via CLAMP
by: Weng, Weiwei, et al.
Published: (2024) -
Lifelong Continual Learning for Anomaly Detection: New Challenges, Perspectives, and Insights
by: Kamil Faber, et al.
Published: (2024-01-01) -
Online semisupervised learning approach for quality monitoring of complex manufacturing process
by: Weng, Weiwei, et al.
Published: (2021) -
Continuous Learning: The Solution to Stay on Digital Labour Market
by: Carmen-Elena BĂNESCU, et al.
Published: (2023-06-01) -
Incorporating a Continuing Professional Development Process into Residency Training
by: Toyin Tofade, et al.
Published: (2014-01-01)