A continual learning method that uses moment-propagation uncertainty to identify important network parameters and regularizes them either by lowering their learning rates or by increasing per-parameter KL penalties.
Learning in nonsta- tionary environments: A survey,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Dynamic Continual Learning: Harnessing Parameter Uncertainty for Improved Network Adaptation
A continual learning method that uses moment-propagation uncertainty to identify important network parameters and regularizes them either by lowering their learning rates or by increasing per-parameter KL penalties.