Growth during training inserts new units into a specialized trajectory, making them forward-active but backward-starved with weaker gradients than existing units.
Online continual learning without the storage constraint.arXiv preprint arXiv:2305.09253
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2verdicts
UNVERDICTED 2representative citing papers
Smooth-Leaky and Randomized Smooth-Leaky activations mitigate loss of plasticity in continual learning by targeting negative-branch shape and saturation behavior.
citing papers explorer
-
On the Stability of Growth in Structural Plasticity
Growth during training inserts new units into a specialized trajectory, making them forward-active but backward-starved with weaker gradients than existing units.
-
Activation Function Design Sustains Plasticity in Continual Learning
Smooth-Leaky and Randomized Smooth-Leaky activations mitigate loss of plasticity in continual learning by targeting negative-branch shape and saturation behavior.