Modeling and contractivity of neural-synaptic networks with Hebbian learning

DOI10.1016/j.automatica.2024.111636zbMath1543.92002MaRDI QIDQ6550233

Giovanni Russo, Bullo, Francesco, Veronica Centorrino

Publication date: 5 June 2024

Published in: Automatica (Search for Journal in Brave)

zbMATH Keywords

nonlinear network systemsHopfield Neural NetworksHebbian/anti-Hebbian learning, contraction theory

Mathematics Subject Classification ID

Neural networks for/in biological studies, artificial life and related topics (92B20)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• A simplified neuron model as a principal component analyzer
• On contraction analysis for non-linear systems
• Mathematical formulations of Hebbian learning
• Transformations by diagonal matrices in a normed space
• Matrix measures, stability and contraction theory for dynamical systems on time scales
• Mathematical Equivalence of Two Common Forms of Firing Rate Models of Neural Networks
• A Differential Lyapunov Framework for Contraction Analysis
• Dynamic properties of neural networks with adapting synapses
• On Logarithmic Norms
• New conditions for global stability of neural networks with application to linear and quadratic programming problems
• Hierarchical Selective Recruitment in Linear-Threshold Brain Networks—Part I: Single-Layer Dynamics and Selective Inhibition
• Unsupervised learning by competing hidden units
• Contraction Analysis of Time-Delayed Communications and Group Cooperation
• Hebbian Learning of Recurrent Connections: A Geometrical Perspective
• Learning representations by back-propagating errors
• Neurons with graded response have collective computational properties like those of two-state neurons.
• A Contraction Approach to the Hierarchical Analysis and Design of Networked Systems
• Non-Euclidean Contraction Theory for Robust Nonlinear Stability

This page was built for publication: Modeling and contractivity of neural-synaptic networks with Hebbian learning