Fast Neural Noise Stabilizes Associative Memory against Slow Synaptic Noise
cond-mat.dis-nn, physics.bio-ph
Submitted: 2026-10-31
Updated: 2026-10-31
License: http://creativecommons.org/licenses/by-nc-sa/4.0/
The gist: Neural systems operate under multi-timescale stochastic dynamics, yet reliably maintain stable functions.
Terminology
Abstract
Neural systems operate under multi-timescale stochastic dynamics, yet reliably maintain stable functions. We investigate how fast neural fluctuations and slow synaptic variability asymmetrically influence the structural robustness of associative memories. While synaptic noise degrades memory formation, neural noise stabilizes the network against structural perturbations. For sequential learning of multiple memories, the average recall performance is maximized at an intermediate neural-noise amplitude, whereas increasing synaptic noise rapidly degrades memory performance. Using an adiabatic mean-field framework, we derive an analytical stationary distribution of stability factors. Our theory reveals that fast neural fluctuations push the system away from marginal stability, serving as an indispensable prerequisite for systemic stability.
Related papers
- Topological metal-insulator transitions in one-dimensional non-Hermitian quasicrystals: beyond PT-symmetry
- Microscopic and collective signatures of feature learning in neural networks
- Synchronous and asynchronous Monte Carlo dynamics of mean-field spin glasses with rotationally invariant couplings: what they share and where they differ
- Reentrant Localization Length in a Quasiperiodic Thue-Morse Chain
- Beyond Ground States: Learning Many-Body Hamiltonians for p-Bit Invertible Arithmetic
- Linear equivalence of nonlinear recurrent neural networks