FTN achieves near-zero forgetting on continual learning benchmarks by isolating task subnetworks via self-organizing binary masks generated through gradient descent, smoothing, and k-winner-take-all.
Supermasks in superposition.Advances in Neural Information Processing Systems, 33:15173– 15184
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Cortex-Inspired Continual Learning: Unsupervised Instantiation and Recovery of Functional Task Networks
FTN achieves near-zero forgetting on continual learning benchmarks by isolating task subnetworks via self-organizing binary masks generated through gradient descent, smoothing, and k-winner-take-all.