An input-dependent weight-generating network combined with EWC retains the first task on MNIST/Fashion-MNIST but learns the second task less accurately than baselines.
Computational principles of synaptic memory consolidation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
EWGN: Elastic Weight Generation and Context Switching in Deep Learning
An input-dependent weight-generating network combined with EWC retains the first task on MNIST/Fashion-MNIST but learns the second task less accurately than baselines.