Storing cycles in Hopfield-type networks with pseudoinverse learning rule: admissibility and network topology

DOI10.1016/j.neunet.2013.06.008zbMath1296.68154arXiv1211.4520OpenAlexW2000467918WikidataQ44474660 ScholiaQ44474660MaRDI QIDQ461174

Gerhard Dangelmayr, Iuliana Oprea, Chuan Zhang

Publication date: 10 October 2014

Published in: Neural Networks (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1211.4520

zbMATH Keywords

admissibilitynetwork topologycyclic patternsHopfield-type networkspseudoinverse learning rule

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Neural networks for/in biological studies, artificial life and related topics (92B20) Permutation groups (20B99)

Related Items

Heteroclinic cycles in Hopfield networks ⋮ Exact inverse matrices of Fermat and Mersenne circulant matrix ⋮ Consecutive and non-consecutive heteroclinic cycles in Hopfield networks ⋮ Algorithms for finding inverse of two patterned matrices over \(\mathbb{Z}_p\) ⋮ Pattern Storage, Bifurcations, and Groupwise Correlation Structure of an Exactly Solvable Asymmetric Neural Network Model ⋮ Determinants of binomial-related circulant matrices

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Learning the pseudoinverse solution to network weights
• Inertia characteristics of self-adjoint matrix polynomials
• Neural theory of association and concept-formation
• The existence of persistent states in the brain
• Learning of oscillatory correlated patterns in a cortical network by a STDP-based learning rule
• Continuous-Time Symmetric Hopfield Nets Are Computationally Universal
• Memory Dynamics in Attractor Networks with Saliency Weights
• The capacity of the Hopfield associative memory
• Patterns of Synchrony in Coupled Cell Networks with Multiple Arrows
• Neural networks and physical systems with emergent collective computational abilities.
• Neurons with graded response have collective computational properties like those of two-state neurons.
• Nonlinear dynamics of networks: the groupoid formalism

This page was built for publication: Storing cycles in Hopfield-type networks with pseudoinverse learning rule: admissibility and network topology