SATURATED OUTPUTS FOR HIGH-GAIN, SELF-EXCITING NETWORKS

DOI10.1142/S0218127491000130MaRDI QIDQ4019530zbMATH OpenOpenAlexFDO

Authors Morris W. Hirsch

Publication date 16 January 1993

Published in International Journal of Bifurcation and Chaos in Applied Sciences and Engineering (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1142/s0218127491000130

zbMATH Keywords

additive neural networks with symmetric weight matricesasymptotic limiting valuesforced outputshigh-gain self-exciting networksHopfield's saturation theoremnetwork of processing unitssigmoidsstable solution

Mathematics Subject Classification ID

Dynamical systems and ergodic theory (37-XX) Learning and adaptive systems in artificial intelligence (68T05) Neural networks for/in biological studies, artificial life and related topics (92B20)

Recommendations

• An analysis on neural dynamics with saturated sigmoidal functions
• Qualitative behaviour of some simple networks
• Linear systems in a saturated mode and convergence as gain becomes large of asymptotically stable equilibrium points of neural nets
• Global asymptotic stability for a linear system in a saturated mode
• scientific article; zbMATH DE number 1195673

Cited in

(1)

• Discrete-time versus continuous-time models of neural networks

This page was built for publication: SATURATED OUTPUTS FOR HIGH-GAIN, SELF-EXCITING NETWORKS

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4019530)