Accelerating neural net dynamics by boundary layer methods

DOI10.1016/0893-9659(93)90041-KMaRDI QIDQ2367988zbMATH OpenOpenAlexFDO

Authors Eric Mjolsness, Willard L. Miranker

Publication date 19 August 1993

Published in Applied Mathematics Letters (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/0893-9659(93)90041-k

zbMATH Keywords

singular perturbationssmall parameterstiff equationsboundary layer methodneural netneuron's transfer function

Mathematics Subject Classification ID

Neural biology (92C20) Nonlinear ordinary differential equations and systems (34A34) Singular perturbations for ordinary differential equations (34E15) Multiple scale methods for ordinary differential equations (34E13) Numerical methods for initial value problems involving ordinary differential equations (65L05)

Recommendations

• Methods of solution of boundary value problems on neural networks
• Fast linear system solution by neural networks
• scientific article; zbMATH DE number 1728391
• Solvable models of layered neural networks based on their differential structure

Cites work

• scientific article; zbMATH DE number 3722011 (Why is no real title available?)
• Neurons with graded response have collective computational properties like those of two-state neurons
• ``Neural computation of decisions in optimization problems

Cited in

(1)

• Using neural networks to accelerate the solution of the Boltzmann equation

This page was built for publication: Accelerating neural net dynamics by boundary layer methods

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2367988)