DMFT for coevolving Hopfield network shows moderate plasticity stabilizes retrieval via positive delayed feedback while excessive plasticity imprints the initial cue and creates spurious attractors.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cond-mat.dis-nn 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
A two-level DMFT tracks bulk and outlier spectral dynamics in wide networks, predicting width-consistent outlier growth and hyperparameter transfer under muP scaling for deep linear nets while noting bulk restructuring for large-output tasks.
citing papers explorer
-
DMFT analysis of Hopfield network with plasticity
DMFT for coevolving Hopfield network shows moderate plasticity stabilizes retrieval via positive delayed feedback while excessive plasticity imprints the initial cue and creates spurious attractors.
-
Spectral Dynamics in Deep Networks: Feature Learning, Outlier Escape, and Learning Rate Transfer
A two-level DMFT tracks bulk and outlier spectral dynamics in wide networks, predicting width-consistent outlier growth and hyperparameter transfer under muP scaling for deep linear nets while noting bulk restructuring for large-output tasks.