An analysis on neural dynamics with saturated sigmoidal functions

DOI10.1016/S0898-1221(97)00208-3zbMath0903.68159OpenAlexW2013106927MaRDI QIDQ1130395

S. H. Smith

Publication date: 14 December 1998

Published in: Computers \& Mathematics with Applications (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/s0898-1221(97)00208-3

zbMATH Keywords

dynamic link networksaturated attractors

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Cites Work

• Unnamed Item
• Unnamed Item
• Convergence theorems for the Kohonen feature mapping algorithms with VLRPs
• Extremes and related properties of random sequences and processes
• Self-organization and associative memory.
• A fast dynamic link matching algorithm for invariant pattern recognition
• The replica-symmetric solution without replica trick for the Hopfield model
• Nonlinear neural networks. II: Information processing.
• Lyapunov Functions for Neural Nets with Nondifferentiable Input-Output Characteristics
• Absolute stability of global pattern formation and parallel memory storage by competitive neural networks
• The capacity of the Hopfield associative memory
• Modeling Brain Function
• Analysis of Linsker's application of Hebbian rules to linear networks
• Qualitative behaviour of some simple networks
• Neural networks and physical systems with emergent collective computational abilities.
• Comments on a derivation and application of the ‘maximum entropy production’ principle

This page was built for publication: An analysis on neural dynamics with saturated sigmoidal functions