On the Critical Capacity of the Hopfield Model
J. Feng, M. Shcherbina, B. Tirozzi
Abstract
We estimate the critical capacity of the zero-temperature Hopfield model by using a novel and rigorous method. The probability of having a stable fixed point is one when α 0.113 for a large number of neurons. This result is an advance on all rigorous results in the literature and the relationship between the capacity α and retrieval errors obtained here for small α coincides with replica calculation results.
Create a lesson
Related papers
A local Yang-Baxter obstruction for the hard-square model
Gabriel Ortega, Eliecer Peña-Ancavil
Concavity of Normalized Generalized Brézin--Gross--Witten Correlators and Its Applications
Chenglang Yang, Xuhui Zhang
Large particle number asymptotics for point-interacting bosons in the plane
Rupert L. Frank, Robert Seiringer
A Counterexample to the Weak Gibbs and Regularity Conjectures
Marius Wesle
Spectral properties of twisted soft waveguides
Pavel Exner, David Spitzkopf
Fluctuating Hydrodynamics of Quantum Fluids from the Nonlinear Fokker-Planck Equation
Mingjian Gu, Zhaoyu Fei, Xiaoguang Wang