Eigenvector dreaming

DOI10.1088/1742-5468/AD138EMaRDI QIDQ6620187zbMATH OpenFDO

Authors Marco H. Benedetti, Louis Carillo, Enzo Marinari, Marc Mézard

Publication date 16 October 2024

Published in Journal of Statistical Mechanics: Theory and Experiment (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.1088/1742-5468/AD138E

zbMATH Keywords

learning theoryneuromorphic modelssynaptic plasticity

Mathematics Subject Classification ID

Statistical mechanics, structure of matter (82-XX)

Recommendations

• Hebbian learning, its correlation catastrophe, and unlearning
• Dreaming neural networks: rigorous results
• On the unlearning procedure yielding a high-performance associative memory neural network
• Hebbian dreaming for small datasets
• A spectral approach to Hebbian-like neural networks

Cites work

• DISTRIBUTION OF EIGENVALUES FOR SOME SETS OF RANDOM MATRICES
• Dreaming neural networks: rigorous results
• Neural networks and physical systems with emergent collective computational abilities
• Statistical mechanics of Hopfield-like neural networks with modified interactions
• The space of interactions in neural network models
• Unlearning in the paramagnetic phase of neural network models

Cited in

(7)

• Interacting dreaming neural networks
• Hebbian dreaming for small datasets
• Regularization, early-stopping and dreaming: a Hopfield-like setup to address generalization and overfitting
• A spectral approach to Hebbian-like neural networks
• Training neural networks with structured noise improves classification and generalization
• Daydreaming algorithm for biased patterns
• Analysis of the Hopfield model incorporating the effects of unlearning

This page was built for publication: Eigenvector dreaming

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6620187)