Dynamical mean-field analysis shows slow dynamics near retrieval boundaries in high-order Hopfield models persist even without diagonal interactions, pointing to intrinsic high-order effects.
Statistical Mechanics of Recurrent Neural Networks II. Dynamics
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
A lecture notes style review of the non-equilibrium statistical mechanics of recurrent neural networks with discrete and continuous neurons (e.g. Ising, graded-response, coupled-oscillators). To be published in the Handbook of Biological Physics (North-Holland). Accompanied by a similar review (part I) dealing with the statics.
fields
cond-mat.stat-mech 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Testing the Role of Diagonal Interactions in High-Order Hopfield Models via Dynamical Mean-Field Theory
Dynamical mean-field analysis shows slow dynamics near retrieval boundaries in high-order Hopfield models persist even without diagonal interactions, pointing to intrinsic high-order effects.