Affine recurrent networks cannot correct errors along state-separating subspaces and thus learn only finite-horizon state tracking that predictably fails when within-class spread exceeds initial between-class separation.
Keller, Carmen Amo Alonso, Terrence J
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Coordinated millisecond-precision spike timing and traveling waves may enable a second tier of cortical activity for long-term working memory via sustained STDP.
citing papers explorer
-
Rethinking State Tracking in Recurrent Models Through Error Control Dynamics
Affine recurrent networks cannot correct errors along state-separating subspaces and thus learn only finite-horizon state tracking that predictably fails when within-class spread exceeds initial between-class separation.
-
Dynamical Mechanisms for Coordinating Long-term Working Memory Based on the Precision of Spike-timing in Cortical Neurons
Coordinated millisecond-precision spike timing and traveling waves may enable a second tier of cortical activity for long-term working memory via sustained STDP.