ECL searches for a separate evolved neural network architecture for each task, archives it as an expert, and reports replay-free continual learning gains over single-model baselines on CIFAR-100 and Tiny-ImageNet.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Achieving Deep Continual Learning via Evolution
ECL searches for a separate evolved neural network architecture for each task, archives it as an expert, and reports replay-free continual learning gains over single-model baselines on CIFAR-100 and Tiny-ImageNet.