Lower bounds on the restitution error in the Hopfield model
This paper analyzes the question of the storage capacity of the Hopfield model. Non-rigorous analytic as well as numerical results suggest that the Hopfield model with \(N\) neurons can store up \(\alpha_cN\) patterns, where \(\alpha_c\approx 0.14\). While it has been proven by \textit{Ch. M. Newman} [Networks 1, 223-238 (1988)] that \(\alpha_c\geq 0.055\), there is no rigorous result that would show that \(\alpha_c<\infty\). The present paper takes a step into this direction by studying the local minima of the Hamiltonian in the neighborhood of one pattern. It is proven that for any \(\alpha>0\), there exists a \(\delta(\alpha)>0\), such that in a ball of radius \(\delta(\alpha)\) (distances are measured by the Hamming distance), there is no local minimum. Furthermore, it is shown than as \(\alpha\) tends to infinity, \(\delta(\alpha)\) becomes larger that 0.05. In spite of the relatively poor numerical result, the paper is interesting to read and contains a number of very nice and original ideas.
- A lower bound for the memory capacity in the Potts-Hopfield model
- On the storage capacity of Hopfield models with correlated patterns
- Moderate deviations for the overlap parameter in the Hopfield model
- On a model of associative memory with huge storage capacity
- The capacity of \(q\)-state Potts neural networks with parallel retrieval dynamics
- Fluctuations of the free energy in the high temperature Hopfield model
- The storage capacity of the Hopfield model and moderate deviations
- Typical error pattern recovery of the Hopfield memory under error-tolerant conditions
- High storage capacity in the Hopfield model with auto-interactions -- stability analysis
- scientific article; zbMATH DE number 919589 (Why is no real title available?)
- scientific article; zbMATH DE number 5022035 (Why is no real title available?)
- The Hopfield model on a sparse Erdös-Renyi graph
- Graph degree sequence solely determines the expected Hopfield network pattern stability
- A spectral approach to Hebbian-like neural networks
- Pattern reconstruction with restricted Boltzmann machines
- Opinion formation in a heterogeneous population --- a new approach to the Hopfield model
- On the capacity of an associative memory model based on neural cliques
This page was built for publication: Lower bounds on the restitution error in the Hopfield model
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q679160)
