A spectral approach to Hebbian-like neural networks

DOI10.1016/j.amc.2024.128689MaRDI QIDQ6585533zbMATH OpenFDO

Authors Elena Agliari, Alberto Fachechi, Domenico Luongo

Publication date 12 August 2024

Published in Applied Mathematics and Computation (Search for Journal in Brave)

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Neural nets applied to problems in time-dependent statistical mechanics (82C32)

Recommendations

• Hebbian learning from first principles
• Recognition of general patterns using neural networks
• High-symmetry Hopfield-type neural networks
• scientific article; zbMATH DE number 2201931
• An expansion of the neural network theory by introducing Hebb postulate

Cites work

• scientific article; zbMATH DE number 3136275 (Why is no real title available?)
• scientific article; zbMATH DE number 4092811 (Why is no real title available?)
• scientific article; zbMATH DE number 7008335 (Why is no real title available?)
• An almost sure large deviation principle for the Hopfield model
• Distributions of Matrix Variates and Latent Roots Derived from Normal Samples
• Dreaming neural networks: rigorous results
• Eigenvector dreaming
• Generalized Guerra's interpolation schemes for dense associative neural networks
• Hebbian dreaming for small datasets
• Hebbian learning from first principles
• Hebbian learning, its correlation catastrophe, and unlearning
• High storage capacity in the Hopfield model with auto-interactions -- stability analysis
• Interacting dreaming neural networks
• Large deviation principles for the Hopfield model and the Kac-Hopfield model
• Lower bounds on the restitution error in the Hopfield model
• Modeling Brain Function
• Neural networks and physical systems with emergent collective computational abilities
• On the Marchenko–Pastur law in analog bipartite spin-glasses
• On the critical capacity of the Hopfield model.
• On the effective initialisation for restricted Boltzmann machines via duality with Hopfield model
• On the storage capacity of Hopfield models with correlated patterns
• On the unlearning procedure yielding a high-performance associative memory neural network
• Random matrices and complexity of spin glasses
• Random matrix methods for machine learning
• Replica symmetry breaking in neural networks with modified pseudo-inverse interactions
• Replica symmetry breaking in neural networks: a few steps toward rigorous results
• Rigorous results on the thermodynamics of the dilute Hopfield model
• Sharp upper bounds on perfect retrieval in the Hopfield model
• Statistical mechanics of Hopfield-like neural networks with modified interactions
• The capacity of the Hopfield associative memory
• The emergence of a concept in shallow neural networks
• The inverse eigenvalue problem of structured matrices from the design of Hopfield neural networks
• The spin-glass phase-transition in the Hopfield model with \(p\)-spin interactions
• Universality of covariance matrices
• ``Neural computation of decisions in optimization problems

Cited in

(3)

• Replica symmetry breaking in supervised and unsupervised Hebbian networks
• Eigenvector dreaming
• Hebbian learning from first principles

This page was built for publication: A spectral approach to Hebbian-like neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6585533)