Compensation type algorithms for neural nets: Stability and convergence

DOI10.1007/BF00275816zbMath0715.92003WikidataQ52118654 ScholiaQ52118654MaRDI QIDQ752028

Ingolf E. Dammasch, Ludwig J. Cromme

Publication date: 1989

Published in: Journal of Mathematical Biology (Search for Journal in Brave)

zbMATH Keywords

stability; convergence; fixed points; connectivity; simulations; behavior; memory; equilibrium state; AMP; cognitive systems; average membrane potential; compensation type algorithm; existence of compensated networks; McCulloch-Pitts networks; neural modeling; Plasticity of synaptic connections; temporal development of neural networks

Mathematics Subject Classification ID

92C20: Neural biology

94C99: Circuits, networks

Related Items

Fixed point theorems for discontinuous functions and applications, A theoretical network model to analyse neurogenesis and synaptogenesis in the dentate gyrus, Fixed point theorems for discontinuous mapping

Cites Work

• Unnamed Item
• Pacemaker neuron model with plastic firing rate: Entrainment and learning ranges
• Self-stabilization of neuronal networks. I. The compensation algorithm for synaptogenesis
• Fixed point theorems for discontinuous mapping
• The computation of fixed points and applications
• ON THE PROPERTIES OF RANDOMLY CONNECTED McCULLOCH-PITTS NETWORKS: DIFFERENCES BETWEEN INPUT-CONSTANT AND INPUT-VARIANT NETWORKS
• Simplicial and Continuation Methods for Approximating Fixed Points and Solutions to Systems of Equations
• A logical calculus of the ideas immanent in nervous activity