Graph degree sequence solely determines the expected Hopfield network pattern stability

DOI10.1162/NECO_A_00685MaRDI QIDQ5380189zbMATH OpenOpenAlexWikidataFDO

Authors Daniel Berend, Shlomi Dolev, Ariel Hanemann

Publication date 4 June 2019

Published in Neural Computation (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1162/neco_a_00685

zbMATH Keywords

Hopfield neural networkpattern stabilitygraph degree sequence

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Applications of graph theory (05C90) Neural networks for/in biological studies, artificial life and related topics (92B20)

Recommendations

• High storage capacity in the Hopfield model with auto-interactions -- stability analysis
• Power law decay of stored pattern stability in sparse Hopfield neural networks
• scientific article; zbMATH DE number 897979
• Analogue neural networks on correlated random graphs
• Asymptotic eigenvectors, topological patterns and recurrent networks

Cites work

• Capacity of an associative memory model on random graph architectures
• Collective dynamics of `small-world' networks
• Emergence of Scaling in Random Networks
• Error detecting and error correcting codes
• Lower bounds on the restitution error in the Hopfield model
• Neural networks and physical systems with emergent collective computational abilities
• On the critical capacity of the Hopfield model.
• Rigorous bounds on the storage capacity of the dilute Hopfield model
• Rigorous results for the Hopfield model with many patterns
• The Hopfield model on a sparse Erdös-Renyi graph
• The capacity of the Hopfield associative memory

Cited in

(1)

• Edge crossings in random linear arrangements

This page was built for publication: Graph degree sequence solely determines the expected Hopfield network pattern stability

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5380189)