High storage capacity in the Hopfield model with auto-interactions -- stability analysis

DOI10.1088/1751-8121/AA8FD7MaRDI QIDQ4597592zbMATH OpenOpenAlexFDO

Authors Jacopo Rocchi, D. Tantari, David Saad

Publication date 13 December 2017

Published in Journal of Physics A: Mathematical and Theoretical (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1704.07741, https://publications.aston.ac.uk/id/eprint/31607/1/Revised_Manuscript.pdf

zbMATH Keywords

capacityHopfield neural networkrecurrent neural networksretrieval abilitystability fixed points

Mathematics Subject Classification ID

Neural networks for/in biological studies, artificial life and related topics (92B20) Neural nets applied to problems in time-dependent statistical mechanics (82C32)

Abstract: Recent studies point to the potential storage of a large number of patterns in the celebrated Hopfield associative memory model, well beyond the limits obtained previously. We investigate the properties of new fixed points to discover that they exhibit instabilities for small perturbations and are therefore of limited value as associative memories. Moreover, a large deviations approach also shows that errors introduced to the original patterns induce additional errors and increased corruption with respect to the stored patterns.

Recommendations

• Storage capacity of a neural network with state-dependent synapses
• Capacity of the Hopfield model
• Lower bounds on the restitution error in the Hopfield model
• scientific article; zbMATH DE number 1121927
• On the storage capacity of generalized Hopfield models

Cites work

• Advanced mean field methods. Theory and practice
• Neural networks and physical systems with emergent collective computational abilities
• Neurons with graded response have collective computational properties like those of two-state neurons

Cited in

(12)

• Non-convex multi-species Hopfield models
• A spectral approach to Hebbian-like neural networks
• Multiple bifurcations and periodic coexistence in a delayed Hopfield two-neural system with a monotonic activation function
• On a model of associative memory with huge storage capacity
• Power law decay of stored pattern stability in sparse Hopfield neural networks
• Dense Hopfield networks in the teacher-student setting
• The dynamics of the Hopfield model for homogeneous weight matrix
• Information storage in high-order neural networks with unequal neural activity
• Graph degree sequence solely determines the expected Hopfield network pattern stability
• Hopfield model with planted patterns: a teacher-student self-supervised learning model
• On the number of spurious memories in the Hopfield model (neural network)
• High-symmetry Hopfield-type neural networks

This page was built for publication: High storage capacity in the Hopfield model with auto-interactions -- stability analysis

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4597592)