Task-irrelevant stimuli create long-term representational drift in task-relevant features, with drift rate increasing with variance and dimension of the irrelevant subspace, across Hebbian and gradient-based learning.
Why do similarity matching objectives lead to hebbian/anti-hebbian networks?Neural computation, 30(1):84–124, 2017
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
q-bio.NC 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Contribution of task-irrelevant stimuli to drift of neural representations
Task-irrelevant stimuli create long-term representational drift in task-relevant features, with drift rate increasing with variance and dimension of the irrelevant subspace, across Hebbian and gradient-based learning.